steering

This paper introduces a general formulation of non-linear intervention for large language models, extending beyond the Linear Representation Hypothesis to manipulate features encoded along non-linear manifolds, and validates the approach on refusal bypass steering.

This paper investigates how large language models process emotional valence through mechanistic interpretability. Using activation patching and steering on three open-source LLMs, the authors find that negative valence is localized to early layers while positive valence peaks in mid-to-late layers, and they validate this through topic-controlled flip tests.