{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/the-hidden-dimensions-of-llm-alignment-a","title":"The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Safety Analysis","arxiv_id":"2502.09674","date":"2025-02-13","proceeding":null,"authors":["Wenbo Pan","Zhichao Liu","Qiguang Chen","Xiangyang Zhou","Haining Yu","Xiaohua Jia"],"abstract":"Large Language Models' safety-aligned behaviors, such as refusing harmful queries, can be represented by linear directions in activation space. Previous research modeled safety behavior with a single direction, limiting mechanistic understanding to an isolated safety feature. In this work, we discover that safety-aligned behavior is jointly controlled by multi-dimensional directions. Namely, we study the vector space of representation shifts during safety fine-tuning on Llama 3 8B for refusing jailbreaks. By studying orthogonal directions in the space, we first find that a dominant direction governs the model's refusal behavior, while multiple smaller directions represent distinct and interpretable features like hypothetical narrative and role-playing. We then measure how different directions promote or suppress the dominant direction, showing the important role of secondary directions in shaping the model's refusal representation. Finally, we demonstrate that removing certain trigger tokens in harmful queries can mitigate these directions to bypass the learned safety capability, providing new insights on understanding safety alignment vulnerability from a multi-dimensional perspective. Code and artifacts are available at https://github.com/BMPixel/safety-residual-space.","url_abs":"https://arxiv.org/abs/2502.09674v2","url_pdf":"https://arxiv.org/pdf/2502.09674v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"the-hidden-dimensions-of-llm-alignment-a","repo_url":"https://github.com/bmpixel/safety-residual-space","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"the-hidden-dimensions-of-llm-alignment-a","repo_url":"https://github.com/rachtibat/lrp-explains-transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"the-hidden-dimensions-of-llm-alignment-a","repo_url":"https://github.com/rachtibat/lrp-for-transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"safety-alignment","task_name":"Safety Alignment"}],"methods":[{"method_slug":"llama","method_name":"LLaMA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.09674","atlas_url":"https://app.syntology.ai/?focus=2502.09674","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2502.09674"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2502.09674\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2502.09674"},"call":"get_concepts_for_paper(arxiv_id=\"2502.09674\")"}],"by_repo":[{"repo":"bmpixel/safety-residual-space","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"rachtibat/lrp-explains-transformers","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2310.01188"],"harvested_for_calls":[{"arxiv_id":"2310.01188","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2310.01188"},"call":"get_harvested_code_for_paper(arxiv_id=\"2310.01188\")"}]},{"repo":"rachtibat/lrp-for-transformers","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"f275b6262986820f5927747a4294e228b7e2ec1c11b2762e05a358bb12882737","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}