© 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. 44907
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to athlete performance and career achievements

    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
    /licenses
    -0.17
    agne
    -0.17
    bare
    -0.17
    bate
    -0.16
     nouve
    -0.15
    GRP
    -0.15
    .cz
    -0.13
     stol
    -0.13
    åį³
    -0.13
    FileVersion
    -0.13
    POSITIVE LOGITS
     games
    0.51
     regular
    0.37
    games
    0.35
     game
    0.34
     Games
    0.34
     Regular
    0.30
    regular
    0.29
    Regular
    0.28
    Games
    0.28
    _games
    0.27
    Activations Density 0.039%

    No Known Activations