© 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. 25319
    Prev
    Next
    INDEX
    Explanations

    references to video content and its promotion

    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
    olumn
    -0.18
     listeners
    -0.15
     photographers
    -0.14
    fte
    -0.14
    ìŀ¡ëĭ´
    -0.13
    olv
    -0.13
    fono
    -0.13
    olta
    -0.13
     Photograph
    -0.13
    uplicates
    -0.13
    POSITIVE LOGITS
     video
    0.93
    video
    0.78
     videos
    0.75
     Video
    0.74
    Video
    0.69
    -video
    0.69
     VIDEO
    0.69
    è§Ĩé¢ij
    0.65
    _video
    0.65
     vid
    0.64
    Activations Density 0.077%

    No Known Activations