© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 22885
    Prev
    Next
    INDEX
    Explanations

    expressions of curiosity or questioning about situations

    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
    วà¸ĩ
    -0.17
    Lite
    -0.15
    Ïĥή
    -0.15
    иÑģлов
    -0.14
     backtrack
    -0.14
    à¸Ĺาà¸Ļ
    -0.14
     thá»į
    -0.14
    apid
    -0.14
    ublik
    -0.14
    averse
    -0.13
    POSITIVE LOGITS
     wonder
    0.41
     wondered
    0.30
    Wonder
    0.29
     Wonder
    0.29
     wondering
    0.29
     wonders
    0.26
     feel
    0.25
     notice
    0.24
     question
    0.22
     feels
    0.21
    Activations Density 0.096%

    No Known Activations