OraCore · Topic ·research
How LLMs encode harmful behavior internally
A pruning study suggests harmful output lives in a compact, shared weight set—helping explain jailbreak brittleness and emergent misalignment.
1 articles in this thread ·Last updated 19h ago·First seen Jul 5, 2026
Timeline
A pruning study suggests harmful output lives in a compact, shared weight set—helping explain jailbreak brittleness and emergent misalignment.