© 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. 55119
    Prev
    Next
    INDEX
    Explanations

    SQL query examples

    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
    EMPLARY
    -0.10
    #region
    -0.09
     Mare
    -0.09
    oho
    -0.09
    658
    -0.09
    ALLERY
    -0.09
    ese
    -0.08
     Hund
    -0.08
    ddf
    -0.08
    //\n\n\n
    -0.08
    POSITIVE LOGITS
    nev
    0.10
    ï½£
    0.10
     contested
    0.10
    unden
    0.10
    redd
    0.09
    #endregion
    0.09
     tr
    0.09
    ste
    0.09
     Rosen
    0.08
    afi
    0.08
    Activations Density 0.133%

    No Known Activations