© 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. 1626
    Prev
    Next
    INDEX
    Explanations

    vÄĥn hóa vÃł dạng

    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
     ÄIJó
    -0.14
    Tại
    -0.13
    NÄĥm
    -0.12
    Bá»Ļ
    -0.12
    Viá»ĩc
    -0.12
     Tiá»ĥu
    -0.12
    ÄIJá»iji
    -0.12
     Giáo
    -0.11
     chắn
    -0.11
     ká»ĭp
    -0.11
    POSITIVE LOGITS
     cho
    0.13
     Ph
    0.12
     ban
    0.11
     ph
    0.11
     Kh
    0.11
     пÑĢоÑĦеÑģÑģионалÑĮ
    0.11
     vÃł
    0.11
    gia
    0.11
     Ban
    0.11
     ÄIJ
    0.11
    Activations Density 0.046%

    No Known Activations