© 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. 41361
    Prev
    Next
    INDEX
    Explanations

    references to international relations and geopolitical dynamics

    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
    (strtolower
    -0.17
    cola
    -0.16
    inho
    -0.15
     widespread
    -0.15
    à¸į
    -0.15
    asıyla
    -0.14
    bourne
    -0.14
    боÑĢ
    -0.14
     Nun
    -0.14
    uries
    -0.14
    POSITIVE LOGITS
     dipl
    0.24
    Washington
    0.23
     Washington
    0.23
    hawks
    0.20
    -security
    0.19
     Kiss
    0.18
     Cold
    0.18
    awks
    0.18
     diplomatic
    0.17
    Cold
    0.17
    Activations Density 0.146%

    No Known Activations