© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 8462
    Prev
    Next
    INDEX
    Explanations

    methods or rules related to web design and font handling

    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
    orf
    -0.15
    overlay
    -0.15
    ç§Ģ
    -0.14
    ¯¯¯¯
    -0.14
     cir
    -0.14
    unity
    -0.13
    ŀĭ
    -0.13
    $MESS
    -0.13
     onDataChange
    -0.13
    .icons
    -0.13
    POSITIVE LOGITS
     Web
    0.30
     HTML
    0.30
     web
    0.24
     browser
    0.24
     UA
    0.24
     DOM
    0.23
     html
    0.23
    Web
    0.23
    WebKit
    0.23
    HTML
    0.22
    Activations Density 0.036%

    No Known Activations