© 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. 26014
    Prev
    Next
    INDEX
    Explanations

    information about actors and their roles in film and theater

    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
    utura
    -0.16
    èŃľ
    -0.16
    dbg
    -0.15
    lá
    -0.15
    ajas
    -0.15
    erer
    -0.14
    incinn
    -0.14
    ypse
    -0.14
    usable
    -0.14
     eldre
    -0.14
    POSITIVE LOGITS
     role
    0.64
     roles
    0.60
    role
    0.51
     Role
    0.48
    -role
    0.46
     Roles
    0.45
    Role
    0.45
    roles
    0.43
    Roles
    0.39
    è§Ĵèī²
    0.39
    Activations Density 0.107%

    No Known Activations