Linear probes for Othello board states factor into tensor-product structure with square and color embeddings composed by a binding matrix, from which the linear probes can be directly recovered.
Learning a generative meta-model of llm activations.arXiv preprint arXiv:2602.06964
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
UniSteer trains a conditional flow matching model on LLM residual-stream activations to enable text-conditioned steering and classification across multiple behavioral tasks.
citing papers explorer
-
Tensor Product Representation Probes Reveal Shared Structure Across Linear Directions
Linear probes for Othello board states factor into tensor-product structure with square and color embeddings composed by a binding matrix, from which the linear probes can be directly recovered.
-
UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM Steering
UniSteer trains a conditional flow matching model on LLM residual-stream activations to enable text-conditioned steering and classification across multiple behavioral tasks.