© 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. 57480
    Prev
    Next
    INDEX
    Explanations

    This is/was/are

    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
    è¿Ļ个
    -0.10
    ëĿ¼ëĬĶ
    -0.10
    ãģ¨ãģĦãģĨ
    -0.09
    ìĿ´ëĿ¼ëĬĶ
    -0.09
    ander
    -0.09
    è¿Ļç§į
    -0.09
    æĺ¯ä¸Ģ个
    -0.08
    λλη
    -0.08
    chet
    -0.08
     Laud
    -0.08
    POSITIVE LOGITS
     ones
    0.14
    ones
    0.13
     Ones
    0.10
     called
    0.10
     Rocket
    0.09
     Called
    0.09
    GX
    0.09
    rites
    0.09
     then
    0.09
    -called
    0.09
    Activations Density 0.096%

    No Known Activations