© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 13026
    Prev
    Next
    INDEX
    Explanations

    references to streaming and Twitch-related content

    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
    ordova
    -0.23
     Zuk
    -0.17
    odom
    -0.15
    ynet
    -0.15
    å¸ĸ
    -0.14
     çĻ¾åº¦
    -0.14
     RELEASE
    -0.14
    ahkan
    -0.14
     dÄ±ÅŁÄ±
    -0.14
     phóng
    -0.14
    POSITIVE LOGITS
     stream
    0.39
     streams
    0.35
     Stream
    0.32
    -stream
    0.31
    .stream
    0.29
     Twitch
    0.29
    stream
    0.29
     twitch
    0.28
    Stream
    0.28
    .twitch
    0.27
    Activations Density 0.009%

    No Known Activations