© 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. 22510
    Prev
    Next
    INDEX
    Explanations

    structures and frameworks related to certification processes

    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
     Frid
    -0.14
    iquer
    -0.14
    ик
    -0.14
    annel
    -0.13
    егоÑĢ
    -0.12
    ĨĴ
    -0.12
    readcr
    -0.12
    ucz
    -0.12
    __()
    -0.12
    elez
    -0.11
    POSITIVE LOGITS
    -fontawesome
    0.19
    unch
    0.15
    AND
    0.14
    DisplayStyle
    0.14
    .gridColumn
    0.14
    íķĻê³¼
    0.14
    ulia
    0.14
    ither
    0.13
    anda
    0.13
    710
    0.13
    Activations Density 0.063%

    No Known Activations