© 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. 46323
    Prev
    Next
    INDEX
    Explanations

    mode or production

    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
    umper
    -0.10
     Unary
    -0.10
     Mend
    -0.09
    ãĤ¥
    -0.09
    radu
    -0.09
     Thom
    -0.09
    WARDED
    -0.09
    wap
    -0.08
    ÑģÑĤиÑĤÑĥ
    -0.08
    ipsis
    -0.08
    POSITIVE LOGITS
     mode
    0.65
     Mode
    0.52
    mode
    0.47
     modes
    0.47
    Mode
    0.45
    -mode
    0.43
    模å¼ı
    0.43
    _mode
    0.40
    .mode
    0.39
     ÑĢежим
    0.37
    Activations Density 0.155%

    No Known Activations