© 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. 63267
    Prev
    Next
    INDEX
    Explanations

    nouns and terms associated with conflict and political events

    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
    raman
    -0.15
    δί
    -0.15
    tring
    -0.15
     Brut
    -0.14
    ycop
    -0.14
    ว
    -0.14
    illions
    -0.14
    ulfilled
    -0.14
    ï¼ģ”↵↵
    -0.14
    дам
    -0.14
    POSITIVE LOGITS
     exactly
    0.25
     just
    0.23
     last
    0.21
     precisely
    0.18
     twice
    0.17
     back
    0.17
    igkeit
    0.16
     in
    0.16
     here
    0.16
    505
    0.15
    Activations Density 0.153%

    No Known Activations