© 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. 21782
    Prev
    Next
    INDEX
    Explanations

    drafts and manuscripts

    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
     Hardcover
    -0.11
    Books
    -0.10
    é¡Į
    -0.10
    isci
    -0.10
     книж
    -0.10
     textbooks
    -0.09
    books
    -0.09
     Books
    -0.09
     novels
    -0.09
     adjacency
    -0.09
    POSITIVE LOGITS
     document
    0.26
     report
    0.21
     draft
    0.21
     essay
    0.19
     body
    0.18
     paper
    0.18
     article
    0.18
    document
    0.18
     text
    0.17
     piece
    0.16
    Activations Density 0.219%

    No Known Activations