© 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. 30581
    Prev
    Next
    INDEX
    Explanations

    references to search operations or search activities

    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
    à¹ģà¸ģ
    -0.17
     casc
    -0.17
    .contents
    -0.16
    zos
    -0.16
    ži
    -0.15
    remen
    -0.15
     Zaman
    -0.14
    žel
    -0.14
    cy
    -0.14
    ega
    -0.14
    POSITIVE LOGITS
    light
    0.26
    ers
    0.25
    lights
    0.24
     for
    0.24
    ingly
    0.20
    LIGHT
    0.18
     kiếm
    0.18
    licht
    0.17
     effort
    0.17
     parties
    0.16
    Activations Density 0.023%

    No Known Activations