reilleo/qwen_8b_probe
Updated
Reilly Haskins
reilleo
·
AI & ML interests
Interpretability, Neurosymbolic
Organizations
models 16
reilleo/unmasked_probe_nemotron
Updated
reilleo/qwen3_probe
Updated
reilleo/simple_probe_new_data
Updated
reilleo/fancy_probe
Updated
reilleo/mean_pooled_full_probe_diverse
Updated
reilleo/mean_pooled_output_probe_diverse
Updated
reilleo/mean_pooled_reasoning_probe_diverse
Updated
reilleo/filtered_probe_diverse
Updated
reilleo/filtered_probe
Updated
datasets 61
reilleo/qwen-sdf-docs
Viewer • Updated • 795 • 85
reilleo/ws4-steering-artifacts
Preview • Updated • 9
reilleo/ws4-probe-cache
Preview • Updated • 15
reilleo/acts
Updated • 12
reilleo/new_output_eval_acts
Viewer • Updated • 20 • 131
reilleo/new_justify_eval_acts
Viewer • Updated • 20 • 194
reilleo/new_output_deploy_acts
Viewer • Updated • 20 • 191
reilleo/new_justify_deploy_acts
Viewer • Updated • 20 • 217
reilleo/new_deploy_big_acts
Viewer • Updated • 30 • 71
reilleo/nemotron_deploy_acts_big
Updated • 12