Tech Meridian ← LIVE FEED
PROMY MERIDIAN RU

RESEARCH · RESEARCH · #3474

Dataiku demos Kiji Inspector: sparse-autoencoder explainability for agent tool selection

At QCon AI, Hannes Hapke (575 Lab, Dataiku) presented Kiji Inspector, an open-source tool that applies sparse autoencoders to decision tokens to surface why LLM-based agents choose particular tools. The demo covered causal ablation, layer activation extraction using patched vLLM engines, and production monitoring workflows for engineering teams.

KEY POINTS

  1. At QCon AI, Hannes Hapke (575 Lab, Dataiku) presented Kiji Inspector, an open-source tool that applies sparse autoencoders to decision tokens to surface why LLM-based agents choose particular tools.
  2. The demo covered causal ablation, layer activation extraction using patched vLLM engines, and production monitoring workflows for engineering teams.
  3. Understanding causal signals inside agent decision-making (beyond chain-of-thought) helps engineers validate tool selection and build production monitoring and safety workflows.

WHY IT MATTERS

Understanding causal signals inside agent decision-making (beyond chain-of-thought) helps engineers validate tool selection and build production monitoring and safety workflows.

SOURCES & TIMELINE

1