© 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. 24134
    Prev
    Next
    INDEX
    Explanations

    actions related to providing aid and protection in a combat scenario

    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
    raj
    -0.15
    arih
    -0.14
    ê·ł
    -0.14
    éĹ²
    -0.14
    åĪĢ
    -0.14
     kapas
    -0.14
    _mt
    -0.14
    ffi
    -0.14
    orman
    -0.13
    æ£Ĵ
    -0.13
    POSITIVE LOGITS
     cover
    0.52
     Cover
    0.40
    cover
    0.39
    -cover
    0.34
     hiding
    0.34
     covers
    0.33
     conceal
    0.33
    Cover
    0.32
    _cover
    0.31
     COVER
    0.31
    Activations Density 0.051%

    No Known Activations