SOURCE-LINKED INTELLIGENCE

Hallucination Neurons and Where to Find Them: An Investigation into the existence of Hallucination Neurons

arXiv · AI, language, vision and robotics · article · Sep 24, 2026 · UTC

Interpretable machine learning for Large Language Models (LLMs) increasingly relies on sparse probing methods that identify small sets of neurons claimed to detect and causally influence behaviors such as factuality recall, safety alignment, and hallucination. These claims have important implications for model auditing and behavioral steering, yet they are rarely tested against known failure modes of $L_1$-regularized probing in correlated, high-dimensional feature spaces. We propose a five-step diagnostic protocol covering feature correlation, bootstrap stability, sparse versus dense ranking

Read original source ↗ Open in workspace

recordType

paper

region

Global