© 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. 30449
    Prev
    Next
    INDEX
    Explanations

    instances of the word "that" and its variations in different contexts

    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
    #echo
    -0.15
    _THAT
    -0.14
    icas
    -0.14
    sip
    -0.14
    umo
    -0.14
    опиÑģ
    -0.13
     нами
    -0.13
    άλι
    -0.13
     knull
    -0.13
    gger
    -0.13
    POSITIVE LOGITS
     while
    0.43
     although
    0.38
    while
    0.32
     if
    0.30
    although
    0.28
     While
    0.28
     since
    0.28
     "
    0.28
     whereas
    0.26
     despite
    0.26
    Activations Density 0.289%

    No Known Activations