© 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. 26028
    Prev
    Next
    INDEX
    Explanations

    statements related to conclusions and reasoning

    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
    à¸ĵ
    -0.17
    andom
    -0.15
    uler
    -0.15
    ABCDEFGHIJKLMNOP
    -0.15
    oran
    -0.15
    eah
    -0.15
    abcdefghijkl
    -0.14
    ájem
    -0.14
     Clar
    -0.14
    elves
    -0.14
    POSITIVE LOGITS
     draw
    0.70
     drawn
    0.63
     Draw
    0.61
     drawing
    0.61
     drew
    0.61
    draw
    0.60
     draws
    0.60
    Draw
    0.56
     DRAW
    0.54
     Drawing
    0.52
    Activations Density 0.034%

    No Known Activations