This work extends the framework that demonstrated that truth representations in large language models are universal across statement polarity but reside within a multidimensional subspace along three questions: how the dimensionality of the subspace depends on the model’s knowledge, which architectural component builds the truth direction, and what the direction is a mixture of.
B\"urger et al.\ (2024) demonstrated that truth representations in large language models are universal across statement polarity but reside within a multidimensional subspace. The truth value of a statement is linearly readable from a residual stream of language model, but it is not clear how much of that representation fits on a single direction, which component builds it, or what it is made of. We conducted a study based on these questions, with one instrument: a training-free axis, the dominant direction of the singular value decomposition (SVD) of hidden-state differences over true/false minimal pairs, identified without labels up to one global sign. Extensive evaluation across 14 models from 6 diverse architectural families (including MoE), read and extract at cost $O(d)$ per token. We close with a pre-registered prediction on whether the arrangement extends to categories whose truth is computed rather than retrieved.
B\"urger et al. (2024) demonstrated that truth representations in large language models are universal across statement polarity but reside within a multidimensional subspace. We extend this framework along three questions: how the dimensionality of the subspace depends on the model's knowledge, which architectural component builds the truth direction, and what the direction is a mixture of. In Part I, a training-free directional probe derived from the SVD of hidden-state minimal pairs shows that the dimensionality of truth is knowledge-dependent: the signal concentrates on a single axis for known facts and diffuses as knowledge decreases. In Part II, a relational law emerges across multiple model families: attention propagates truth frames, the feed-forward network opposes the current block's frame, and post-peak decay is causally attributed to the SwiGLU value stream. Furthermore, per-category truth axes form a semantically signed arrangement that converges across families. Stress tests expose a sign instability in this orientation, which we repair with a spectral consensus gauge to sharpen the convergence into a knowledge-gated law. Finally, a replication campaign on Gemma-2-2b, extending our decomposition tools to accommodate its sandwich normalization, confirms these laws and attributions. We quantify the knowledge gate as classical attenuation and isolate a stable, model-specific private geometry.
Francesco Vicidomini· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
