will these methods work for large models?

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• We hypothesize that sparse autoencoders or similar methods will work on frontier large language models, though significant computational challenges remainhypothesis0.791
  Forward-looking prediction about scalability of the method to larger models
• Features can be used to steer large models.claim0.783
  Clamping feature activations causally alters model behavior in interpretable ways.
• Does DAS scale with large foundation models?question0.762
  Practical scalability question addressed in Appendix D.
• Representation engineering for large-language models: Survey and research challenges (Bartoszcze et al., 2025)concept0.745
  Survey of representation engineering methods cited as related work
• Bigger models are more likely to converge to a shared representation than smaller modelshypothesis0.743
  Selective pressure toward convergence via model capacity
• Larger models should amplify bias less than smaller models, with model biases more accurately reflecting data biases rather than exacerbating themclaim0.737
  Implication of PRH for AI fairness and bias
• we have shown a mathematical relationship between the two modelsquote0.732
  Core claim distinguishing this paper's contribution from looser representational similarity arguments.
• Today's Large Language Models have become so good at playing Turing's game that it often takes experts to demonstrate the present limits of their ability to simulate human-like intelligence.claim0.729
  Paper's assessment of current LLM capabilities relative to Turing Test