© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 41091
    Prev
    Next
    INDEX
    Explanations

    instances of conflict or tension involving threats and opposing parties

    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
    Forgery
    -0.16
    æ¨
    -0.15
    tür
    -0.14
    kyt
    -0.14
    лаж
    -0.14
    eum
    -0.14
    cctor
    -0.13
    gree
    -0.13
    .BorderFactory
    -0.13
    Prostit
    -0.13
    POSITIVE LOGITS
     threat
    1.00
     threats
    0.96
     Threat
    0.95
     threaten
    0.91
     threatened
    0.91
    threat
    0.91
     threatening
    0.88
    -threat
    0.86
     threatens
    0.83
    -threatening
    0.66
    Activations Density 0.034%

    No Known Activations