© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 25261
    Prev
    Next
    INDEX
    Explanations

    python code imports and libraries

    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
     Zig
    -0.10
     Ele
    -0.10
     /*
    -0.10
     ele
    -0.09
    emailer
    -0.09
    zon
    -0.09
     Brady
    -0.09
     exec
    -0.09
     furniture
    -0.09
    vor
    -0.08
    POSITIVE LOGITS
    åĿĬ
    0.09
    pect
    0.09
     Client
    0.09
    kwargs
    0.09
     threading
    0.09
    );\\n
    0.09
    _kwargs
    0.09
    \\n
    0.09
    lient
    0.09
    (None
    0.08
    Activations Density 0.058%

    No Known Activations