© 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. 24289
    Prev
    Next
    INDEX
    Explanations

    phrases indicating denial or defense in a controversial context

    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
    imed
    -0.15
    eur
    -0.14
    iem
    -0.14
    ulumi
    -0.14
    ovice
    -0.14
    eko
    -0.14
    лоп
    -0.13
     stunt
    -0.13
    585
    -0.13
    ksen
    -0.13
    POSITIVE LOGITS
     engaged
    0.98
     engage
    0.97
     engagement
    0.95
     engaging
    0.90
    engage
    0.88
     Eng
    0.87
     engages
    0.86
     Engagement
    0.83
    Eng
    0.82
    eng
    0.75
    Activations Density 0.026%

    No Known Activations