© 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. 22173
    Prev
    Next
    INDEX
    Explanations

    references to software development and legacy technology usage

    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
    plotlib
    -0.14
    гаÑĢ
    -0.14
    pii
    -0.14
     unlink
    -0.14
    ermint
    -0.14
    heid
    -0.14
     verk
    -0.13
     selfies
    -0.13
    veloper
    -0.13
     screenshots
    -0.13
    POSITIVE LOGITS
     flash
    1.30
     Flash
    1.27
    Flash
    1.18
    flash
    1.13
     FLASH
    1.06
    -flash
    1.04
    _flash
    0.94
    FLASH
    0.91
    .flash
    0.88
     flashes
    0.81
    Activations Density 0.012%

    No Known Activations