Steer Features

Use this skill for feature-level steering of models — locating the internal feature that drives a target behavior, scoring and selecting it by its effect on the model's output, and directly amplifying or shrinking that feature's activation during generation to control behavior. Applies to features read from the model's own activations or from a Sparse Autoencoder (SAE); the bundled demo scripts happen to use an SAE, but the method does not require one.

zjunlp Updated 1.5k repo stars

File contents

zjunlp/mechanist commit fca23610b6

Frequently asked questions

npx get-skill add zjunlp/steer-features