© 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. 28886
    Prev
    Next
    INDEX
    Explanations

    negations or expressions of denial

    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
    chwitz
    -0.16
    launcher
    -0.15
    κÏģι
    -0.15
     Lawson
    -0.14
    ÑĪев
    -0.14
    ком
    -0.14
    ivant
    -0.14
     nháºŃt
    -0.14
    ương
    -0.14
    opis
    -0.14
    POSITIVE LOGITS
     alone
    0.34
    alone
    0.29
     Alone
    0.29
    -alone
    0.25
    alon
    0.18
     defined
    0.17
     solo
    0.17
     lone
    0.16
     obligation
    0.16
     definition
    0.15
    Activations Density 0.013%

    No Known Activations