© 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. 25347
    Prev
    Next
    INDEX
    Explanations

    references to online content creators and their audience engagement

    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
     Borg
    -0.15
    ovol
    -0.15
    .Generated
    -0.14
    .baidu
    -0.14
    .linkedin
    -0.14
    sms
    -0.13
    .poster
    -0.13
    vendor
    -0.13
    malink
    -0.13
    -placeholder
    -0.13
    POSITIVE LOGITS
     YouTube
    0.43
    YouTube
    0.36
     content
    0.32
     stream
    0.32
     You
    0.31
     channel
    0.30
     influ
    0.30
     youtube
    0.30
     streams
    0.29
     channels
    0.28
    Activations Density 0.076%

    No Known Activations