Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 29338
    Prev
    Next
    INDEX
    Explanations

    instances of action related to rescue and survival 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
    yen
    -0.16
    598
    -0.15
    kud
    -0.15
    ť
    -0.15
    ["$
    -0.14
    982
    -0.14
    OffsetTable
    -0.14
    /Branch
    -0.14
     depos
    -0.13
    rodu
    -0.13
    POSITIVE LOGITS
     deck
    0.54
     decks
    0.48
     Deck
    0.47
    deck
    0.42
    Deck
    0.41
     crew
    0.35
     decking
    0.33
    _deck
    0.33
     hull
    0.33
     stern
    0.33
    Activations Density 0.025%

    No Known Activations