Posts in tags: "Mechanistic Interpretability" (4 posts)
Two natively-trained 1-bit LLMs converge on the same activation anomaly without ever sharing weights. A note on convergence under pressure.
Read More about The Two Models That Never Met. Both Measured at the Same Depth.Two natively-trained 1-bit LLMs lose the four-stage circuit that organizes fp16 transformers. Behavior survives; structure dissolves.
Read More about When the Circuit DissolvesA LarQL patch deletes 'Paris is the capital of France' from a frozen LLM. The receipt is a 100-byte JSON file with a SHA-256 checksum.
Read More about Deleting Paris from a Language ModelEvery modern LLM converges on the same four-stage circuit. We map the architecture and what its absence in 1-bit models means.
Read More about The Architecture Every Language Model Converges To
