© 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. 58726
    Prev
    Next
    INDEX
    Explanations

    request some

    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
    ones
    -0.08
    åħ¨éĥ¨
    -0.08
    VN
    -0.08
    .MILLISECONDS
    -0.08
     ÑĢÑĥкÑĥ
    -0.07
    éĢ¸
    -0.07
    \App
    -0.07
    asso
    -0.07
    åħ¨éĿ¢
    -0.07
    DMI
    -0.07
    POSITIVE LOGITS
     some
    0.58
    some
    0.44
    ä¸ĢäºĽ
    0.42
     Some
    0.40
    Some
    0.37
    äºĽ
    0.32
     einige
    0.31
     bazı
    0.31
     quelques
    0.29
    .some
    0.29
    Activations Density 0.263%

    No Known Activations