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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 30610
    Prev
    Next
    INDEX
    Explanations

    details related to sports statistics and player roles in a team

    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
     recep
    -0.16
    itten
    -0.15
    shade
    -0.14
    modo
    -0.14
    çak
    -0.13
    лÑİд
    -0.13
     Hizmet
    -0.13
    ofday
    -0.13
    oldt
    -0.13
    uars
    -0.13
    POSITIVE LOGITS
     trainer
    0.19
     play
    0.16
     match
    0.16
     matches
    0.16
     Coupe
    0.15
     Trainer
    0.15
     debut
    0.15
    inoa
    0.15
    aka
    0.15
     Training
    0.14
    Activations Density 0.026%

    No Known Activations