Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 45
    Prev
    Next
    INDEX
    Explanations

    references to installation and setup procedures

    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
    VML
    -0.17
    /xhtml
    -0.15
    ÅĻet
    -0.15
    /ajax
    -0.15
     XHTML
    -0.14
    Ajax
    -0.14
    à¹īว
    -0.13
    (æĹ¥
    -0.13
    /GPL
    -0.13
    -ajax
    -0.13
    POSITIVE LOGITS
     Py
    0.16
     react
    0.15
    atron
    0.14
     Mond
    0.14
     ng
    0.14
    Teams
    0.14
     py
    0.14
    IFT
    0.13
     Node
    0.13
     Alfred
    0.13
    Activations Density 0.134%

    No Known Activations