© 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. 25477
    Prev
    Next
    INDEX
    Explanations

    sales data and statistics related to video games

    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
     Talent
    -0.17
    xac
    -0.15
    ÏĨι
    -0.15
     talent
    -0.14
     talents
    -0.14
    esson
    -0.14
    รม
    -0.14
    oji
    -0.14
    oteca
    -0.14
    rahim
    -0.14
    POSITIVE LOGITS
     sales
    0.49
     Sales
    0.39
    sales
    0.38
     sell
    0.36
    Sales
    0.36
     sells
    0.33
    -sales
    0.33
     sold
    0.33
    -selling
    0.32
     selling
    0.32
    Activations Density 0.057%

    No Known Activations