© 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. 21340
    Prev
    Next
    INDEX
    Explanations

    references to sources or claims

    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
    stm
    -0.19
    ski
    -0.17
    edException
    -0.17
    nt
    -0.17
    leigh
    -0.17
     migrationBuilder
    -0.16
    Ïĥια
    -0.16
    haus
    -0.16
    sWith
    -0.16
    endas
    -0.15
    POSITIVE LOGITS
    ting
    0.23
    izens
    0.21
    TING
    0.21
    zelf
    0.20
    gerald
    0.19
    tle
    0.19
    à¸Ľà¸£à¸°à¸¡à¸²à¸ĵ
    0.19
    inerary
    0.19
    TY
    0.19
    iless
    0.18
    Activations Density 0.038%

    No Known Activations