© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 44926
    Prev
    Next
    INDEX
    Explanations

    references to book publication, including first editions and remaining volumes

    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
    ิà¸ŀ
    -0.17
    дÑı
    -0.17
    Ñĩай
    -0.15
     Articles
    -0.13
    /editor
    -0.12
    Badge
    -0.12
    adla
    -0.12
     Brow
    -0.12
    ditor
    -0.12
    ugar
    -0.12
    POSITIVE LOGITS
     book
    1.27
    book
    1.02
     Book
    0.97
    Book
    0.95
    -book
    0.94
     BOOK
    0.89
    _book
    0.86
     books
    0.81
    .book
    0.79
    (book
    0.79
    Activations Density 0.031%

    No Known Activations