© 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. 55340
    Prev
    Next
    INDEX
    Explanations

    key concepts related to psychological states, awareness, and complex systems

    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
     and
    -0.19
     or
    -0.16
    à¹ģละà¸ģาร
    -0.14
    LIK
    -0.14
    üçük
    -0.14
    timeofday
    -0.14
     ë°ı
    -0.13
    implify
    -0.13
    .cmb
    -0.13
    à¹ģละส
    -0.13
    POSITIVE LOGITS
    bt
    0.14
    uli
    0.13
    esto
    0.13
    s
    0.13
    hd
    0.13
    ily
    0.13
    zh
    0.13
    chin
    0.13
    bies
    0.13
    RELATED
    0.13
    Activations Density 0.002%

    No Known Activations