© 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. 56523
    Prev
    Next
    INDEX
    Explanations

    divided into sections

    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
    wards
    -0.10
    582
    -0.09
     forth
    -0.09
    esome
    -0.09
    iest
    -0.09
    xes
    -0.09
    834
    -0.09
    æ¾
    -0.09
    icity
    -0.09
    ican
    -0.09
    POSITIVE LOGITS
    /div
    0.13
     sẻ
    0.12
    ided
    0.12
    ials
    0.12
    (div
    0.11
    ISION
    0.11
    DED
    0.11
    al
    0.11
    isors
    0.11
    isions
    0.10
    Activations Density 0.028%

    No Known Activations