© 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. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 44718
    Prev
    Next
    INDEX
    Explanations

    references to books and reading activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -navbar
    -0.15
    /editor
    -0.14
    theid
    -0.14
    estead
    -0.14
    ÏĩÏĮ
    -0.13
    aphael
    -0.13
    ras
    -0.13
     éĻ
    -0.13
    lexical
    -0.13
     Letter
    -0.13
    POSITIVE LOGITS
     books
    0.56
    books
    0.42
     book
    0.41
    -books
    0.41
     Books
    0.39
    Books
    0.38
    _books
    0.36
     BOOK
    0.35
    -book
    0.32
     книги
    0.31
    Activations Density 0.109%

    No Known Activations