© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 25910
    Prev
    Next
    INDEX
    Explanations

    update and click actions

    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
    ToAdd
    -0.11
    HeaderValue
    -0.11
    /Dk
    -0.10
    _mC
    -0.10
    HeaderCode
    -0.10
    CreatedBy
    -0.10
    CreatedAt
    -0.10
    HttpGet
    -0.10
    _added
    -0.10
    Inserted
    -0.10
    POSITIVE LOGITS
     update
    0.38
     Update
    0.37
    update
    0.34
    Update
    0.33
     updating
    0.32
    .update
    0.32
     UPDATE
    0.31
    æĽ´æĸ°
    0.31
    .Update
    0.30
    _update
    0.29
    Activations Density 0.045%

    No Known Activations