© 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. 18518
    Prev
    Next
    INDEX
    Explanations

    ask about

    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
    nap
    -0.10
     Doll
    -0.10
    aurus
    -0.09
     elo
    -0.09
     Hudson
    -0.09
    lek
    -0.09
    ANTE
    -0.09
    rial
    -0.08
    addon
    -0.08
    392
    -0.08
    POSITIVE LOGITS
     ask
    0.30
    让
    0.30
     asks
    0.27
     asking
    0.26
    ï¼Į让
    0.25
     let
    0.25
    ask
    0.25
     à¤ķरव
    0.25
    Ask
    0.25
    ãģķãģĽãĤĭ
    0.25
    Activations Density 0.263%

    No Known Activations