taylorsatula/prompt-mechinterp

End-to-end pipeline for seeing how LLMs actually process your prompts. Capture attention across every layer, render heatmaps and cooking curves, compare variants with evidence — not vibes.

2 best points · 1 comments · 1 Hacker News post · 46 GitHub stars · View on GitHub

Hacker News discussions

• From vibes to data: measuring how LLMs attend to your prompt, layer by layer (2 points, 1 comments, by taylorsatula, 2026-03-06)