© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 54104
    Prev
    Next
    INDEX
    Explanations

    references to Bitcoin and its market dynamics

    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
     Broadcom
    -0.14
    tero
    -0.14
    вÑĸлÑĮ
    -0.14
     Bever
    -0.14
    ë²Į
    -0.14
    èį
    -0.14
    ronym
    -0.14
     bom
    -0.13
    _sta
    -0.13
    елик
    -0.13
    POSITIVE LOGITS
     Bit
    0.46
     bit
    0.43
    -bit
    0.40
    Bit
    0.40
    _bit
    0.39
     Bitcoin
    0.38
    bit
    0.38
    .bit
    0.36
     биÑĤ
    0.36
    /bit
    0.35
    Activations Density 0.085%

    No Known Activations