© 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 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. 43297
    Prev
    Next
    INDEX
    Explanations

    phrases related to safety and danger

    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
    ymi
    -0.15
     hacks
    -0.14
    æĬĺ
    -0.14
    stÅĻÃŃ
    -0.14
     Reeves
    -0.14
    ниÑĩеÑģ
    -0.14
    uppen
    -0.14
    InstantiationException
    -0.14
    gnore
    -0.14
    ekim
    -0.14
    POSITIVE LOGITS
     danger
    0.99
     dangerous
    0.91
    danger
    0.87
     dangers
    0.86
     Danger
    0.85
    Danger
    0.82
    -danger
    0.78
     Dangerous
    0.77
    åį±
    0.75
     hazardous
    0.72
    Activations Density 0.026%

    No Known Activations