© 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. 19310
    Prev
    Next
    INDEX
    Explanations

    rejected or denied

    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
     refrain
    -0.11
     exem
    -0.10
     Kens
    -0.10
    fone
    -0.10
    Warn
    -0.09
    INGLE
    -0.09
     Warn
    -0.09
    ABL
    -0.09
     Rein
    -0.09
    åĿĬ
    -0.09
    POSITIVE LOGITS
     rejection
    0.47
     rejected
    0.44
     reject
    0.43
    æĭĴ
    0.39
    .reject
    0.36
     rejects
    0.35
     rejecting
    0.34
     Reject
    0.33
    reject
    0.33
    Reject
    0.33
    Activations Density 0.102%

    No Known Activations