© 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. 21137
    Prev
    Next
    INDEX
    Explanations

    legislative processes and voting activities

    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
    rů
    -0.15
     dame
    -0.15
    aton
    -0.15
    ÄĽti
    -0.14
    esson
    -0.14
    atos
    -0.14
    izo
    -0.14
    PLUGIN
    -0.14
    chet
    -0.14
     Dame
    -0.14
    POSITIVE LOGITS
     vote
    0.59
     votes
    0.49
     Vote
    0.44
    vote
    0.44
    Vote
    0.39
     voted
    0.38
     voting
    0.36
    _vote
    0.36
     Votes
    0.35
    votes
    0.34
    Activations Density 0.063%

    No Known Activations