AINeutralarXiv – CS AI · Apr 77/10
🧠
How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models
Researchers identified a sparse routing mechanism in alignment-trained language models where gate attention heads detect content and trigger amplifier heads that boost refusal signals. The study analyzed 9 models from 6 labs and found this routing mechanism distributes at scale while remaining controllable through signal modulation.