© 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. 1445
    Prev
    Next
    INDEX
    Explanations

    ëĭ¤ìĭľ ìĹ´

    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
     ë¨
    -0.13
     ë¸
    -0.12
    bé
    -0.10
    alic
    -0.10
    ìĿ´ê°Ģ
    -0.09
     amet
    -0.09
     Morg
    -0.09
     Cherry
    -0.09
     заÑıв
    -0.09
    onia
    -0.08
    POSITIVE LOGITS
    utow
    0.10
    ints
    0.09
    @nate
    0.09
     createState
    0.09
    atter
    0.09
    .idx
    0.09
     Bran
    0.09
    ÙħÙĨت
    0.09
     intim
    0.08
    oustic
    0.08
    Activations Density 0.056%

    No Known Activations