Every checkpoint behind the cross-uplift figure: shared init, six 50/50 arms (midtrain + RL 25/50/100), all-families reference run.
de schamphelaere PRO
ceselder
AI & ML interests
None yet
Recent Activity
updated a model about 13 hours ago
ceselder/modulation-lens-rl-8x1024-summaryAR-step_100 published a model about 13 hours ago
ceselder/modulation-lens-rl-8x1024-summaryAR-step_100 updated a model about 16 hours ago
ceselder/modulation-lens-rl-8x1024-summaryAR-step_50Organizations
Training data and LoRAcles and LoRAcles for llama 3.3 70B, qwen3-14b and olmo-3-32B
Models and Datasets from Building Better Activation Oracles
Every checkpoint behind the cross-uplift figure: shared init, six 50/50 arms (midtrain + RL 25/50/100), all-families reference run.
Here are the checkpoints of various methods I am working on for qwen 3.6 27B
Training data and LoRAcles and LoRAcles for llama 3.3 70B, qwen3-14b and olmo-3-32B
a multi token J lens approach that may or may not be abandoned, here are a bunch of checkpoints
Models and Datasets from Building Better Activation Oracles
OOD model organisms for LoRAcle emergent-behavior eval — 4 Betley EM LoRAs + Cloud subliminal owl + EM training data.