Activation Steering

Toward Latent Language Model Skills Steering and Optimization: An Empirical Study
Skills, as a useful abstraction for the procedural capabilities of large language models (LLMs), capture how models perform structured, …
PDF
Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering
SOPHIA detects when a model repeats unproductive reasoning states and intervenes through hidden-state steering. The method uses transitions between reasoning states to guide generation, improving answer quality and token efficiency.
PDF