Representation Engineering

Use this skill when working with Representation Engineering (RepE) for AI transparency, monitoring, or controlling internal representations of large language models including truthfulness detection, emotion control, harmlessness steering, and memorization analysis.

zjunlp Updated 1.5k repo stars

File contents

zjunlp/mechanist commit 81f59d5545

Frequently asked questions

npx get-skill add zjunlp/representation-engineering