© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13966
    Prev
    Next
    INDEX
    Explanations

    phrases related to player performance and versatility in sports

    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
     stellar
    -0.16
    rchive
    -0.15
     solid
    -0.15
    oliday
    -0.15
    Solid
    -0.15
     equally
    -0.14
     ole
    -0.14
     Solid
    -0.14
    .dsl
    -0.14
    REA
    -0.14
    POSITIVE LOGITS
     weird
    0.15
    stuff
    0.15
    åįĵ
    0.15
    pheres
    0.15
    .tx
    0.14
    ilon
    0.14
    é¡Į
    0.14
    vid
    0.14
    داÙħ
    0.14
    .heroku
    0.14
    Activations Density 0.001%

    No Known Activations