© 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. 28224
    Prev
    Next
    INDEX
    Explanations

    phrases related to rescue and bravery in critical situations

    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
     yasak
    -0.15
    apon
    -0.15
    asser
    -0.14
    idunt
    -0.14
    ubu
    -0.14
    .CodeAnalysis
    -0.14
    ersh
    -0.14
    obus
    -0.13
    arrant
    -0.13
    iggs
    -0.13
    POSITIVE LOGITS
     save
    0.71
     saving
    0.69
     saved
    0.68
     saves
    0.67
     rescue
    0.64
     Save
    0.61
    save
    0.60
     Saving
    0.57
    .save
    0.57
    -saving
    0.57
    Activations Density 0.055%

    No Known Activations