How to Steer the Behavior of a Model: The Refusal Case
Registration
About Event
Primo seminario online della community italiana AIS4I.
Questo seminario si terrà su zoom in lingua inglese con Q&A sia in inglese che in italiano.
Abstract
An introduction to AI interpretability through a practical example: identifying the internal mechanisms of LLMs responsible for refusal and steering the behavior accordingly.
Speaker: Enrico Bottazzi
Bio: Enrico is a researcher with a background in cryptography who is now exploring mechanistic interpretability, focusing on understanding how AI models work internally.
Linkedin: 3nricobottazzi
Personal blog: https://www.leku.ink/