Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 9
    Prev
    Next
    INDEX
    Explanations

    interactions and emotional dynamics in relationships

    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
    êu
    -0.17
    รม
    -0.16
    luž
    -0.16
     traumat
    -0.16
    CurrentValue
    -0.16
    ढ
    -0.14
    лÑĥб
    -0.14
    à¥ģà¤ĸ
    -0.14
     dolor
    -0.14
     оÑīÑĥÑī
    -0.14
    POSITIVE LOGITS
     temper
    0.41
     Temper
    0.29
     temp
    0.26
    tem
    0.25
     anger
    0.25
    Tem
    0.25
     tantr
    0.24
     rage
    0.24
     temperament
    0.24
     explode
    0.24
    Activations Density 0.041%

    No Known Activations