© 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. 41609
    Prev
    Next
    INDEX
    Explanations

    verbs related to giving, choosing, and spending time, often in the context of actions and 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
     me
    -0.35
    让æĪij
    -0.33
    ç»ĻæĪij
    -0.32
     us
    -0.31
     themselves
    -0.28
     itself
    -0.27
     мне
    -0.26
     their
    -0.26
     my
    -0.25
    à¸ľà¸¡
    -0.25
    POSITIVE LOGITS
     ourselves
    1.00
     our
    0.57
    ours
    0.52
    our
    0.46
     ours
    0.43
    æĪij们çļĦ
    0.42
     noss
    0.41
     наÑĪиÑħ
    0.40
    Our
    0.39
     nuestros
    0.39
    Activations Density 0.230%

    No Known Activations