AI brief
A LessWrong post presents the first part of a planned research exploration into LLM geometries, building on work by Arditi et al. on the refusal direction in LLMs, using unsupervised methods.
Written by AI from LessWrong's published text.
Source
“Introduction This is the first part of what we plan to be a research exploration into the geometries of LLMs. We start with building off existing work by Arditi et al focused on the refusal direction in LLMs. Background We recommend reading the Arditi et al.”
Interpretation or community commentary rather than straight reporting.
Read original story ↗