© 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. 15331
    Prev
    Next
    INDEX
    Explanations

    instances of communication or contact between individuals

    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
    але
    -0.16
    reon
    -0.16
     Calls
    -0.15
    hin
    -0.15
    лÑĥг
    -0.15
    Calls
    -0.15
    adele
    -0.14
    ught
    -0.14
    _calls
    -0.14
    \Bridge
    -0.14
    POSITIVE LOGITS
     ask
    0.32
     asking
    0.28
    ask
    0.26
     asks
    0.26
     express
    0.25
     request
    0.25
     asked
    0.24
     Ask
    0.23
    express
    0.23
     Express
    0.23
    Activations Density 0.082%

    No Known Activations