© 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. 60447
    Prev
    Next
    INDEX
    Explanations

    you can/will

    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
     Cant
    -0.09
    ãĢĢãĢĢãĢĢãĢĢ ãĢĢ
    -0.09
     Aust
    -0.09
    ​\n\n
    -0.09
    monton
    -0.09
     cant
    -0.09
    ãĤĽ
    -0.08
     banda
    -0.08
    833
    -0.08
    ç«Ł
    -0.08
    POSITIVE LOGITS
     can
    0.18
    åı¯ä»¥
    0.16
    'll
    0.15
     pouvez
    0.14
    ï¼Įåı¯ä»¥
    0.14
    ’;ll
    0.14
     можеÑĤе
    0.13
     need
    0.13
     dapat
    0.13
    abilirsiniz
    0.12
    Activations Density 0.022%

    No Known Activations