© 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. 4773
    Prev
    Next
    INDEX
    Explanations

    salutations, sections, categories

    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
    ..
    -0.09
     Laur
    -0.09
    .opengl
    -0.07
    HING
    -0.07
    anmar
    -0.07
     âĸ²
    -0.07
    agle
    -0.07
    ToLeft
    -0.07
     SWAT
    -0.07
    /rfc
    -0.07
    POSITIVE LOGITS
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.11
    IIIK
    0.10
    ï¾Ŀ
    0.09
     ​​
    0.09
    EEDED
    0.08
    ĥĿ
    0.08
     Scarborough
    0.08
    _Impl
    0.08
    ="">
    0.07
     coquine
    0.07
    Activations Density 0.593%

    No Known Activations