Qwen-2.5-14B mean KL divergence on Alpaca prompts after truth-direction ablation is 0.038

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

• The difficulty boundary for truth directions replicates across all four tested models (Llama-3.2-3B, Llama-3.1-8B, Gemma-2-2b, Gemma-2-9b); generalization to F3-F5 remains consistently low regardless of model size or family.finding0.771
  Establishes generalizability of the core difficulty-boundary finding across model families.
• Truth-related directions reliably emerge at 60–75% of normalized layer depth in Qwen and Gemma modelsfinding0.763
  Experiment 1 finding localizing where truth can be causally mediated
• Suppressing deception/roleplay SAE features in LLaMA 3.3 70B yields 0.96±0.03 consciousness affirmation rate; amplification yields only 0.16±0.05 (z=8.06, p=7.7×10⁻¹⁶)finding0.749
  Core result of Experiment 2: deception feature suppression sharply increases experience claims
• Reflection direction features achieve AUROC 0.772 vs. 0.736 for final layer baseline on deepseek-llama-8b on GSM8k correctness predictionfinding0.746
  Supports claim that uncertainty is encoded in reflection direction
• Clear accuracy stratification across three reflection levels on cruxeval_o_adv: Triggered (.065/.247) > Intrinsic (.040/.133) > No Reflection (.017/.051) for Qwen2.5-3B/Gemma3-4B-ITfinding0.740
  Core empirical result validating the three-level reflection framework on code reasoning.
• Deception feature amplification yields only 0.16 ± 0.05 consciousness affirmation rate in LLaMA 3.3 70B under self-referential processingfinding0.736
  Experiment 2 aggregate amplification result showing amplifying deception features strongly suppresses consciousness claims
• QwQ-32B on MATH-500: 21.0% reasoning token reduction at intervention strength -0.96 with only 0.34% accuracy lossfinding0.734
  Demonstrates reflection redundancy in stronger model on harder math benchmark
• Suppression of deception features produces higher TruthfulQA accuracy (M=0.44) than amplification (M=0.20), t(816)=6.76, p=1.5×10⁻¹⁰ across 29 categoriesfinding0.733
  Out-of-domain generalization showing deception features track general representational honesty