LLMs Build Code Answers in Hidden Layers before They Appear, Revealing Blind Spots in Accuracy Metrics
The paper shows that decoder‑only LLMs first “brew” a solution across many early transformer layers, making it linearly recoverable long before it becomes self‑decodable. Only about 42% of attempts resolve correctly, with depth‑dependent drops, exposing failure modes that standard pass/fail scores miss. Their dual diagnostic—layer probing plus Context‑Stripped Decoding—maps this lifecycle across 16 models.