© 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. 9137
    Prev
    Next
    INDEX
    Explanations

    references to violence and its impact

    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
    ัศ
    -0.16
    ÅĻev
    -0.14
    jit
    -0.14
    IJľ
    -0.14
    afür
    -0.14
    ednou
    -0.13
    ught
    -0.13
    rice
    -0.13
    erosis
    -0.13
    erdale
    -0.13
    POSITIVE LOGITS
     violence
    1.11
     Violence
    1.02
    Viol
    0.93
     violent
    0.92
    -viol
    0.87
    viol
    0.86
     Viol
    0.82
    violent
    0.79
     velocity
    0.77
     viol
    0.76
    Activations Density 0.007%

    No Known Activations