Huginn-0125 does not demonstrate clear stages of inference due to repeated normalization of the residual stream suppressing massive activations

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

• Huginn-0125 performance remains constant when extrapolating beyond training recurrences, while Ouro performance deteriorates in the same regimefinding0.816
  Correlates stable fixed-point behavior with out-of-domain generalization performance at test-time
• Stages of inference metrics (ColSum concentration, mixing score) remain broadly consistent even for the GSM8k prompt exhibiting the largest orbit amplitude in Huginn-0125finding0.794
  Demonstrates robustness of inference stages to non-fixed-point limiting behavior
• Without system prompt, only approximately 0.02% of Huginn-0125 tokens exhibit non-fixed-point (orbit/slider) behavior on GSM8kfinding0.760
  Establishes that non-fixed-point limiting behaviors are extremely rare in practice for the primary experimental setting
• Retrofitted Llama attention patterns converge after the first recurrence and Huginn-0125 immediately following the preludefinding0.751
  Demonstrates remarkably fast convergence to cyclic fixed point behavior in retrofitted models
• Patching h[1] with a divergent representation can activate distinct, hidden pathways that result in misleadingly confirmatory behavior and/or undetected behavior.quote0.745
  Load-bearing description of the core pernicious divergence mechanism illustrated in Figure 1
• probably helps not only with faithful reconstruction but also creates interference patterns that encode nuanced information about the deltas and convergences between states.quote0.735
  Key quote connecting path redundancy to interferometric information encoding.
• All induction heads fall in an extreme corner of high OV eigenvalue positivity and high QK eigenvalue positivity, confirming the mechanistic theoryclaim0.735
  Quantitative verification that the copying and matching structure predicted by the mechanistic theory is present in all observed induction heads
• Under the Markov blanket assumption together with NESS, a generalised synchrony appears, such that the dynamics of internal states can be cast as performing inference over external states via minimisation of variational free energy.claim0.733
  Key theoretical claim linking active inference to physics in Section 2.