© 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. 22582
    Prev
    Next
    INDEX
    Explanations

    I eat, we are

    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
    anko
    -0.09
     |/
    -0.09
    ãĢĢï¾ī
    -0.09
    iers
    -0.09
    ẩu
    -0.09
    ikat
    -0.09
    dojo
    -0.08
    ipel
    -0.08
    702
    -0.08
    ä¸Ģå¹´
    -0.08
    POSITIVE LOGITS
    åĨł
    0.11
    Äł
    0.09
    .heroku
    0.09
    <v
    0.09
     jenter
    0.08
     Brill
    0.08
    modulo
    0.08
    .IsNullOr
    0.08
    <article
    0.08
    ago
    0.08
    Activations Density 0.096%

    No Known Activations