© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 44115
    Prev
    Next
    INDEX
    Explanations

    facial expressions indicating emotional states

    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
    ilon
    -0.17
    egin
    -0.17
    urette
    -0.16
    buzz
    -0.15
    osu
    -0.15
    BindingUtil
    -0.14
    xAB
    -0.14
    .FontStyle
    -0.14
    rollo
    -0.14
    xac
    -0.14
    POSITIVE LOGITS
     expression
    0.46
     expressions
    0.43
     Expression
    0.39
    -expression
    0.37
     facial
    0.36
    Expression
    0.36
    expression
    0.35
     expres
    0.33
     Express
    0.31
    Expressions
    0.31
    Activations Density 0.051%

    No Known Activations