© 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. 24342
    Prev
    Next
    INDEX
    Explanations

    outlier detection

    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
    leta
    -0.10
     tom
    -0.09
    ä¸į足
    -0.09
    reta
    -0.09
     blur
    -0.09
    chai
    -0.09
    vern
    -0.08
     duct
    -0.08
    trak
    -0.08
    alse
    -0.08
    POSITIVE LOGITS
     Out
    0.18
     isolation
    0.15
     Mah
    0.14
    Out
    0.14
     Extreme
    0.13
     mah
    0.13
     Dixon
    0.13
     extreme
    0.13
    _out
    0.13
    lier
    0.13
    Activations Density 0.029%

    No Known Activations