AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Endogenous Resistance to Activation Steering in Language Models

Alex McKenzie, Keenan Pepper, Stijn Servaes, Martin Leitgab, Murat Cubuktepe, Michael Vaiana, Diogo S de Lucena, Judd Rosenblatt, Michael S. A. Graziano

ICML 2026 · Large language models › Language, safety and interpretability · approach: Task vectors and steering · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
append self-monitoring meta-prompt to the prompt (ablation)Llama-3.3-70B · Steered ESRmulti-attempt rate: 7.4% to 31.7%Improved
append self-monitoring meta-prompt to the prompt (ablation)Llama-3.3-70B · Steered ESRESR rate: 3.8% to 14.8%Improved
keep the self-correction-associated latents active (versus zero-ablating them) (ablation)Llama-3.3-70B · Steered ESRESR rate: 3.8% to 2.8%Improved
keep the self-correction-associated latents active (versus zero-ablating them) (ablation)Llama-3.3-70B · Steered ESRmulti-attempt rate: 7.4% to 5.5%Improved
zero-ablate the latents (effect on first-attempt quality) (ablation)Llama-3.3-70B · Steered ESRmean first-attempt score: 26.3 -> 27.4No clear effect
ablate random matched latents instead of the targeted ones (ablation)Llama-3.3-70B · Steered ESRESR rate: 3.8% to 4.2%No clear effect
zero-ablate the latents on held-out prompts (ablation)Llama-3.3-70B · Held-out prompts (20 prompts)ESR rate: reduces it by 30-45%Improved
add a length-matched on-topic prefix before steered continuation (ablation)Llama-3.3-70B · Matched-prefix (447 episodes)continuation relevance score: 8.7 -> 30.4 (+21.8)Improved
use natural post-correction text rather than a generic on-topic prefix (ablation)Llama-3.3-70B · Matched-prefix (447 episodes)continuation relevance score: 30.4 -> 54.5; +45.8 vs +21.8Improved
prefill off-topic text into an unsteered model rather than steering (ablation)Llama-3.3-70B · Prefilling controlself-correction success: ~50% -> ~95%Improved
fine-tune on more masked self-correction data (ablation)Llama-3.1-8B · Steered ESRcorrection improvement rateNo clear effect
fine-tune on higher ratio of self-correction data (10% to 90%) (ablation)Llama-3.1-8B · Steered ESRmulti-attempt rateImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy