© 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. 21742
    Prev
    Next
    INDEX
    Explanations

    references to hockey players and their 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
     Nun
    -0.16
     Gravity
    -0.16
    ัà¸ģษ
    -0.15
    _DIALOG
    -0.14
    èĿ
    -0.14
    setQuery
    -0.14
    ocks
    -0.14
     López
    -0.14
    ł
    -0.13
    spread
    -0.13
    POSITIVE LOGITS
     NHL
    0.16
     Virt
    0.16
     Pou
    0.16
     Tk
    0.16
    Tk
    0.16
    emens
    0.16
    gin
    0.15
     Patri
    0.15
    alsy
    0.15
     goal
    0.15
    Activations Density 0.084%

    No Known Activations