© 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. 21906
    Prev
    Next
    INDEX
    Explanations

    references to sports events and player statistics

    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
    Portland
    -0.18
     Portland
    -0.18
     Northwestern
    -0.17
     Winchester
    -0.16
     Sacramento
    -0.16
    inqu
    -0.16
    ieux
    -0.16
    ento
    -0.16
     Capitol
    -0.15
     Northwest
    -0.15
    POSITIVE LOGITS
     Jets
    0.52
    Jets
    0.44
     Jet
    0.39
     NY
    0.39
     jets
    0.38
    NY
    0.35
    jets
    0.35
    Jet
    0.35
     jet
    0.33
     NYC
    0.31
    Activations Density 0.022%

    No Known Activations