© 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. 35900
    Prev
    Next
    INDEX
    Explanations

    гггггг

    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
    iв
    -0.10
    ******č\n
    -0.10
    mtree
    -0.10
    nitÅĻ
    -0.09
    ypi
    -0.09
    %E
    -0.09
    contri
    -0.09
    chyb
    -0.09
    ProgressHUD
    -0.09
    μιλοÏĤ
    -0.09
    POSITIVE LOGITS
    -
    0.12
    ing
    0.11
    [
    0.11
    ly
    0.11
    ...
    0.11
    ie
    0.11
    --
    0.11
    '
    0.11
    "
    0.10
    ia
    0.10
    Activations Density 0.226%

    No Known Activations