© 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. 44408
    Prev
    Next
    INDEX
    Explanations

    statements regarding societal expectations and pressures, particularly those affecting identity and community integration

    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
    Ľå»º
    -0.16
     stable
    -0.15
    ibold
    -0.15
    aki
    -0.14
    _PS
    -0.14
     Fare
    -0.14
    urat
    -0.14
    oose
    -0.14
    ť
    -0.13
     stead
    -0.13
    POSITIVE LOGITS
     conform
    0.27
     conformity
    0.25
     toe
    0.23
     bow
    0.20
     somehow
    0.19
     Toe
    0.19
     conforms
    0.19
     Bow
    0.18
     towing
    0.18
    Toe
    0.18
    Activations Density 0.126%

    No Known Activations