© 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. 22859
    Prev
    Next
    INDEX
    Explanations

    phrases indicating listener engagement or acknowledgment

    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
    away
    -0.15
     Quantity
    -0.15
    Ãł
    -0.15
    ffa
    -0.15
    avou
    -0.14
     inappropriate
    -0.14
     such
    -0.14
    unday
    -0.14
    sav
    -0.14
     Away
    -0.14
    POSITIVE LOGITS
     correctly
    0.51
    correct
    0.43
     correct
    0.40
     Correct
    0.40
    Correct
    0.38
    _correct
    0.33
     correctamente
    0.31
    orrect
    0.30
    .correct
    0.30
    æŃ£ç¡®
    0.29
    Activations Density 0.010%

    No Known Activations