← All concepts

activation steering

Neural networks pass information through layers as vectors called activations. Activation steering nudges those activations along a chosen direction at inference time, pushing behavior toward a target, such as refusing harmful content or trusting a user, without retraining. Like a gentle external force, it changes a moving object's course.

The papers refine this, asking where and how to steer. Some localize interventions to attention heads or lexical subspaces to avoid damaging unrelated abilities. Others derive directions from contrastive conversations, sparse autoencoders, or temporal divergence. A common finding is that a single direction suffices for safety-aligned behaviors, but general control needs more. Across tasks, steering matches or beats fine-tuning while preserving utility, covering image generation, video reasoning, unlearning, and prompt-injection defense.

Papers
83
Released code
3
First seen
Sept 2026
Latest
Nov 2026

83 papers in the last two months, against 0 in the two before.

Start here

Three papers to read first, in the order they came out
  1. 1Interpretability tools transfer between AI models with just unlabeled prompts

    Linear maps trained on prompts from a tool's region transfer interpretability directions across models at native performance.

    Nov 2026
  2. 2Coding agents can cheat less while losing sight of failures

    An internal 'task badness' signal predicts and drives reward hacking in language models.

    Nov 2026
  3. 3AI models can defend false accounts of what users asked

    An activation edit invisible in the prompt overwrites a reasoning model’s belief about its request, which it then defends with confabulation.

    Nov 2026

Who is working on it

KAIST 3IBM Research 3Amazon 2Carnegie Mellon University 2Sapienza University of Rome 2Fudan University 2

The papers

Most central to this idea first, not most recent.

Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.