© 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. 26181
    Prev
    Next
    INDEX
    Explanations

    hyperlinks and URLs related to web services and data processing

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    pts
    -0.18
    pill
    -0.16
    pitch
    -0.15
    PK
    -0.14
    hower
    -0.14
    Pitch
    -0.14
    paste
    -0.14
    оби
    -0.14
    umbnail
    -0.14
    é³¥
    -0.14
    POSITIVE LOGITS
     page
    1.11
     Page
    0.97
    Page
    0.90
    page
    0.85
    -page
    0.85
     pages
    0.84
    _page
    0.83
     pag
    0.82
     PAGE
    0.80
    .page
    0.78
    Activations Density 0.017%

    No Known Activations