© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 7886
    Prev
    Next
    INDEX
    Explanations

    making decision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    898
    -0.09
    909
    -0.09
    ivas
    -0.09
    ede
    -0.09
    uche
    -0.09
     ãĢĥ
    -0.08
     consum
    -0.08
     Fre
    -0.08
     fres
    -0.08
     Kahn
    -0.08
    POSITIVE LOGITS
     decision
    0.52
    decision
    0.42
     Decision
    0.39
    Decision
    0.36
     decisions
    0.33
    åĨ³å®ļ
    0.33
     quyết
    0.31
    _decision
    0.31
     decide
    0.30
    åĨ³
    0.27
    Activations Density 0.043%

    No Known Activations