Some activation capping settings slightly improve performance on IFEval, MMLU Pro, or GSM8k for both Qwen and Llama

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

• Activation capping reduces harmful response rate by nearly 60% without impacting performance on IFEval, MMLU Pro, GSM8k, and EQ-Benchfinding0.833
  Main quantitative result demonstrating effectiveness of activation capping
• DeepSeek-R1 Llama 8b gains 0.16% accuracy on GSM8k with positive intervention (more reflections) at cost of ~2000 additional tokensfinding0.779
  Only model showing marginal benefit from increased reflection, at substantial token cost
• Optimal activation capping layers for Llama 3.3 70B are layers 56-71 (out of 80) at 25th percentile capfinding0.779
  Specific implementation finding for Llama capping parameters
• Ablating massive activations from Retrofitted Llama (zeroing MLP output in layer 2) eliminates stages of inference comparable to the feedforward modelfinding0.764
  Causal evidence that massive activations are required for stages of inference to emerge in looped models
• Optimal activation capping layers for Qwen 3 32B are layers 46-53 (out of 64) at 25th percentile capfinding0.746
  Specific implementation finding for Qwen capping parameters
• Qwen 2.5 7B has higher Elo scores for 'methodical' and 'formal' traits compared to Llama 3.1 8B which prefers 'colloquial'finding0.743
  Model-specific baseline personality difference revealed by revealed preferences experiment
• Multi-attempt improvement rate peaks at 83% around -1.0σ below threshold in Llama-3.3-70Bfinding0.742
  Shows slightly weaker steering allows more successful corrections, characterizing optimal ESR conditions
• Model activation along the assistant axis drifts steadily away from the assistant pole as conversation shifts toward Aura behavior in Qwen 3 32B, and activation capping eliminates Aura behaviorfinding0.739
  Finding confirming that the Aura persona shift is real, trackable, and causally relevant in persona space