GateWatch: Monitoring LLMs with Tiny Boolean Circuits over SAE Features
The problem: many monitors, none you can read If you run an LLM in production, you eventually want to know what it is doing internally. Is it about to refuse? Is a particular behavior active? Is it following an injected instruction? A common answer is an activation probe: a small classifier trained…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-11-19 18:08 · DEV Community — Machine Learning
GateWatch: Monitoring LLMs with Tiny Boolean Circuits over SAE Features