Hallucination Detection · Mechanistic

A blog and newsletter on Activation-based LLM reliability and hallucination detection.

Cover illustration for “Induction Heads and In-Context Learning Mechanisms”

Featured Mechanistic

Induction Heads and In-Context Learning Mechanisms

Summary Researchers trace in-context learning to a simple copying circuit in transformers.

Dmitri Voloshyn11 min read

Latest articles

  1. Hallucination Detection

    Activation-Based Hallucination Detection in Transformer Decoders

    Reading hidden neuron activity reveals hallucinations before language models finish speaking.

    Dmitri Voloshyn9 min read