Litcius/Paper detail

Steering Llama 2 via Contrastive Activation Addition

Nina Rimsky, Nick Gabrieli, Julian Schulz, Meg Tong, Evan Hubinger, Alexander Turner

202427 citationsDOIOpen Access PDF

Abstract

Nina Rimsky, Nick Gabrieli, Julian Schulz, Meg Tong, Evan Hubinger, Alexander Turner. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Topics & Concepts

Computer scienceInteractive and Immersive Displays