© 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. 8811
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of investigating or conducting inquiries

    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
    edException
    -0.17
    teenth
    -0.16
    itter
    -0.16
     à¹Ĩ
    -0.16
    iets
    -0.15
    ities
    -0.15
    Æł
    -0.14
    ITTER
    -0.14
    KO
    -0.14
    tere
    -0.14
    POSITIVE LOGITS
    ors
    0.19
    ES
    0.18
     into
    0.18
     thoroughly
    0.17
    es
    0.16
    ally
    0.16
     Into
    0.15
    atio
    0.15
    rvine
    0.15
     INTO
    0.14
    Activations Density 0.034%

    No Known Activations