© 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. 63101
    Prev
    Next
    INDEX
    Explanations

    third party service providers

    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
    :animated
    -0.09
    <|begin_of_text|>
    -0.09
    _rq
    -0.07
    biên
    -0.07
    įng
    -0.07
     targetType
    -0.07
    WARDED
    -0.07
    Calibri
    -0.07
    άÏģÏĩ
    -0.07
    uien
    -0.07
    POSITIVE LOGITS
    ultipartFile
    0.08
     поба
    0.07
     Cin
    0.07
    quito
    0.07
     ifstream
    0.07
     useHistory
    0.06
     [{"
    0.06
    ,
    0.06
    .scalablytyped
    0.06
    /as
    0.06
    Activations Density 0.219%

    No Known Activations