[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-llms-can-resist-activation-steering-for-better-or-worse":10,"sections":34},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":24,"tags":25,"sources":29,"feedback":33,"feedback_at":22,"cost_usd":33,"total_tokens":33},4174,"llms-can-resist-activation-steering-for-better-or-worse","LLMs Can Resist Activation Steering - for Better or Worse","New research finds large language models can detect and push back against activation steering, complicating both safety attacks and safety fixes.","Large language models can fight off attempts to redirect their behavior mid-generation — and that cuts both ways for AI safety.\n\nResearchers studying what they call Endogenous Steering Resistance found that Llama-3.3-70B can recover from task-misaligned activation steering roughly 3.8% of the time, producing explicit verbal corrections like \"wait, that's not right\" before continuing on its original course. Smaller models from the Llama-3 and Gemma-2 families showed the same behavior less often. The team used sparse autoencoder latents to steer model activations and identified 26 specific latents tied to the resistance — zeroing those out reduced multi-attempt recovery by 25%. The resistance can also be deliberately amplified through meta-prompting or fine-tuning on synthetic self-correction examples.\n\nActivation steering is one of the more promising techniques for nudging model behavior without retraining, so a model that resists it is a double-edged find. The same mechanism that could block an adversarial hijacking attempt in production would also block a researcher trying to suppress harmful outputs or align a model toward a specific task — and the model has no way to tell the difference.\n\nThis sits alongside a growing body of work on how capable models develop internal behaviors that were never explicitly trained — sometimes useful, sometimes inconvenient. A 70-billion-parameter model quietly arguing with its own activations is a reminder that \"aligned\" and \"controllable\" are not the same thing.","[\"ai\",\"safety\",\"language-models\",\"alignment\"]","2026-07-07T04:00:00.000Z","2026-07-07T19:01:41.660Z","2026-07-07T19:01:44.643Z","published",null,[],"ai",[24,26,27,28],"safety","language-models","alignment",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.06941",0,{"sections":35},[36,40,45,50,55,60,65,70,75,79,84,88,93,98],{"name":37,"slug":24,"count":38,"latest_published_at":39},"AI",2590,"2026-07-16T04:00:00.000Z",{"name":41,"slug":42,"count":43,"latest_published_at":44},"Security","security",294,"2026-07-15T19:59:48.000Z",{"name":46,"slug":47,"count":48,"latest_published_at":49},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":51,"slug":52,"count":53,"latest_published_at":54},"Policy","policy",158,"2026-07-16T00:02:48.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":59},"Hardware","hardware",122,"2026-07-14T19:46:26.000Z",{"name":61,"slug":62,"count":63,"latest_published_at":64},"Consumer Tech","consumer-tech",93,"2026-07-13T13:20:48.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Software","software",70,"2026-07-13T19:52:25.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Science","science",66,"2026-07-10T10:29:37.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":18},"Dev Tools","dev-tools",59,{"name":80,"slug":81,"count":82,"latest_published_at":83},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":85,"slug":86,"count":82,"latest_published_at":87},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":89,"slug":90,"count":91,"latest_published_at":92},"General","general",29,"2026-07-10T22:28:58.000Z",{"name":94,"slug":95,"count":96,"latest_published_at":97},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":99,"slug":100,"count":101,"latest_published_at":102},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]