© 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. 5377
    Prev
    Next
    INDEX
    Explanations

    low or small values

    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
    Not in Any Lists

    No Comments

    Negative Logits
     fewer
    -0.11
    æ¬ł
    -0.10
     McKay
    -0.10
    iano
    -0.10
     Suff
    -0.10
     simplest
    -0.09
     Gib
    -0.09
     useless
    -0.09
    lep
    -0.09
     worthless
    -0.09
    POSITIVE LOGITS
     minor
    0.34
     small
    0.26
    minor
    0.25
     Minor
    0.23
     slight
    0.22
    Minor
    0.22
     minimal
    0.20
    small
    0.20
     nhá»ı
    0.20
     marginal
    0.19
    Activations Density 0.063%

    No Known Activations