Alessandro Stolfo

3
Papers
14
Total Citations

Papers (3)

MIB: A Mechanistic Interpretability Benchmark

ICML 2025
9
citations

Dense SAE Latents Are Features, Not Bugs

NeurIPS 2025
5
citations

Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?

ICML 2024
0
citations