assistant-axis
Jupyter Notebook
★ 1
updated 4mo ago
⑂ fork
The Assistant Axis is a direction in activation space that captures how "Assistant-like" a model's behavior is. Models can drift away from the Assistant during conversations—sometimes toward bizarre or harmful personas. This repo contains a pipeline for generating the Assistant Axis and notebooks for monitoring and steering with it.
No plain-English explanation yet — one is being written right now. Check back in a minute.