© 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. 44339
    Prev
    Next
    INDEX
    Explanations

    technical terminology and comparisons in the context of web development and programming

    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
    .xhtml
    -0.15
     UNICODE
    -0.15
    .gameserver
    -0.15
    InputBorder
    -0.14
    .SizeType
    -0.14
    URLException
    -0.14
    [$_
    -0.13
    à¸Ĥว
    -0.13
    RuntimeObject
    -0.13
    оиÑĤ
    -0.13
    POSITIVE LOGITS
     regular
    0.51
     traditional
    0.50
     plain
    0.48
     ordinary
    0.47
     conventional
    0.46
     normal
    0.46
     standard
    0.42
    regular
    0.39
    traditional
    0.37
    æĻ®éĢļ
    0.37
    Activations Density 0.142%

    No Known Activations