itsalissonsilva
/

Restriction-Learning-Experiment

interpretability

instruction-following

Model card Files Files and versions

Restriction-Learning-Experiment

Commit History

Nov 7 2 days ago

01:50
Explain model applications and add concrete examples; apply requested names

itsalissonsilva

Verified signature
d7f2b0f

Oct 31 9 days ago

06:56
Release exact Forensics restriction adapter with public weights, layer/strength evidence, controls and Gemma terms

itsalissonsilva

Verified signature
9fbaf4c
04:51
Correct donor capture to exact generation-prefill patch sites; verify all 26 self-restorations

itsalissonsilva

Verified signature
8cb2b5d
04:44
Measure Gemma/Qwen steering, probes, causal patching and paired activations

itsalissonsilva

Verified signature
3a3cb6b
04:09
Measure restriction adapter layer likelihood, activations and spectra

itsalissonsilva

Verified signature
914c04f
03:14
Check exact matched-batch restoration

itsalissonsilva

Verified signature
dbadf70
03:11
Train and evaluate selective restrictions with blanket/random controls

itsalissonsilva

Verified signature
efc3f02
03:03
initial commit

itsalissonsilva

Verified signature
8b3e099