Patching h[1] with a divergent representation can activate distinct, hidden pathways that result in misleadingly confirmatory behavior and/or undetected behavior.

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

• Off-manifold divergences can activate hidden pathways that produce misleadingly confirmatory behavior while the true mechanism is never exercisedclaim0.842
  Core claim about why pernicious divergence undermines mechanistic conclusions
• probably helps not only with faithful reconstruction but also creates interference patterns that encode nuanced information about the deltas and convergences between states.quote0.806
  Key quote connecting path redundancy to interferometric information encoding.
• Divergent representations are a common, if not likely, outcome of causal interventions across a wide range of methodsclaim0.789
  Core empirical claim of the paper supported by both theoretical proof and empirical demonstration
• Patching group (b) hidden states (over clause-ending punctuation, early-middle layers) in LLaMA-2-13B produces the strongest causal effect on TRUE/FALSE output predictionsfinding0.786
  Localizes truth representations to specific hidden states, motivating the rest of the analysis
• Future models with substantially increased capabilities will exhibit alignment faking that is more consistent, robust, and harder to detecthypothesis0.784
  Extrapolation from scale-emergence finding to future risk
• Larger hidden representations create more random structure that DAS can search through, allowing manipulation of counterfactual behavior even in randomly initialized networkshypothesis0.781
  Tested in Section 4.4 calibration experiment; confirmed by findings.
• Minimizing divergence magnitude does not guarantee elimination of hidden pathways; it only reduces the risk surfaceclaim0.780
  Important caveat to the CL loss solution, noting it is a step not a complete fix
• When it is not okay, how can we prevent divergent representations from occurring?question0.777
  Third core research question motivating the CL loss approach in Section 5