646-Steering and Monitoring AI Models

Paper Talk · Mar 16, 2026 · 21m

Researchers have developed a scalable method called the Recursive Feature Machine (RFM) to identify and manipulate the internal knowledge of artificial intelligence models. By extracting linear concept representations, this approach allows for model steering, which can adjust model behavior toward specific semantic notions like languages, political stances, or coding proficiency. The study demonstrates that this technique improves AI safety and performance across various architectures, often surpassing the effectiveness of traditional prompting. Furthermore, these internal features prove…