Institution profile

Goodfire AI

Industry researcheurope · gb
Official website
Research library34linked papers
Opportunities0open roles
Selected work

Representative Papers

Are language models aware of the road not taken? Token-level uncertainty and hidden state dynamics

Nov 06, 2025

This work investigates whether large language models (LLMs) implicitly represent unselected reasoning paths—i.e., “untraversed chains of thought”—during text generation. Method: We propose an uncertainty quantification framework based on dynamic analysis of hidden states: (i) decoding intermediate-layer activations to predict future token distributions, and (ii) conducting activation intervention experiments to assess hidden-state sensitivity to multi-path competition. Contribution/Results: We demonstrate that hidden states not only encode the current token decision but also explicitly embed the geometric structure of alternative reasoning paths in latent space. Crucially, the degree of uncertainty encoded in these states strongly correlates with model controllability—i.e., the ease with which generation can be steered toward desired outputs. This study provides the first empirical evidence for LLMs possessing “path awareness” and establishes a principled, interpretable linkage among hidden-state representations, predictive uncertainty, and generation controllability.

1 citationsRead paper
Recent publications

Latest Papers

A Graph Signal Processing Perspective on Numerical Sequence Representations in LLM In-Context Learning

Aug 03, 2026

This study investigates how large language models organize internal representations of numerical sequences during in-context learning. It introduces, for the first time, a systematic application of graph signal processing by treating the token graph induced by attention mechanisms as a weighted graph, with hidden states serving as node signals, and analyzes its spectral properties. The findings reveal that as context length increases, simple inputs yield globally connected graphs with smooth signals, whereas complex inputs lead to localized connectivity and stronger high-frequency components. This pattern consistently emerges across multiple model families, uncovering an intrinsic relationship between the dynamic complexity of inputs and the spectral characteristics of internal representations.

0 citationsRead paper