© 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. 24929
    Prev
    Next
    INDEX
    Explanations

    import pandas numpy matplotlib

    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
    (
    -0.11
    ero
    -0.09
    -l
    -0.09
    -d
    -0.09
    -
    -0.09
    earer
    -0.09
    -s
    -0.09
     Rug
    -0.09
    er
    -0.09
    auga
    -0.09
    POSITIVE LOGITS
    Scalars
    0.10
    .ToShort
    0.10
    ê¸Ķ
    0.09
    warnings
    0.09
    agh
    0.09
    ActionCode
    0.09
    fec
    0.09
     import
    0.09
    UsageId
    0.09
     ImportError
    0.09
    Activations Density 0.039%

    No Known Activations