© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 28360
    Prev
    Next
    INDEX
    Explanations

    topics related to death and challenges faced by groups or organizations

    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
    uer
    -0.14
     (~(
    -0.14
    rett
    -0.14
    .scalablytyped
    -0.14
     Scar
    -0.14
    à¸ĺ
    -0.14
    urga
    -0.13
    emez
    -0.13
     excer
    -0.13
    á»ķi
    -0.13
    POSITIVE LOGITS
    ampp
    0.14
     Tos
    0.13
    .NotNil
    0.13
    nbsp
    0.13
    quete
    0.13
    quet
    0.13
    addon
    0.13
    roken
    0.13
    apyrus
    0.13
    adium
    0.13
    Activations Density 0.042%

    No Known Activations