© 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. 39571
    Prev
    Next
    INDEX
    Explanations

    technical structured code

    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
     taxed
    -0.09
     Lingu
    -0.09
     éĺ
    -0.09
    ););\n
    -0.09
    IRTUAL
    -0.09
    åĩºåĵģ
    -0.08
    lify
    -0.08
    ARCHAR
    -0.08
    /mainwindow
    -0.08
    utta
    -0.08
    POSITIVE LOGITS
     code
    0.20
    code
    0.15
     Struct
    0.14
     programming
    0.14
     technical
    0.13
     structured
    0.13
    structured
    0.13
    Structured
    0.13
    代çłģ
    0.13
    .code
    0.12
    Activations Density 0.172%

    No Known Activations