© 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. 15715
    Prev
    Next
    INDEX
    Explanations

    discussions around legislative procedures and political decisions

    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
    åł¡
    -0.15
    buat
    -0.15
    ห
    -0.14
    Ïħγ
    -0.14
     inaug
    -0.14
    otel
    -0.14
     Romney
    -0.14
    UTOR
    -0.14
    odu
    -0.13
    rades
    -0.13
    POSITIVE LOGITS
     Commons
    0.27
     motions
    0.25
     motion
    0.25
     Lords
    0.24
     Motion
    0.24
    -motion
    0.22
    Motion
    0.21
     Bill
    0.20
     Hans
    0.20
    motion
    0.19
    Activations Density 0.035%

    No Known Activations