Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 23435
    Prev
    Next
    INDEX
    Explanations

    specific character names or references in a video game-related context

    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
     tomorrow
    -0.18
     lately
    -0.15
    มาย
    -0.15
    ë§¹
    -0.14
     yesterday
    -0.14
     recent
    -0.14
     hopefully
    -0.14
    Æł
    -0.13
     next
    -0.13
    orias
    -0.13
    POSITIVE LOGITS
     originally
    0.35
    Originally
    0.29
     original
    0.29
     Originally
    0.29
     initially
    0.27
     ultimately
    0.24
    origin
    0.24
    original
    0.23
     ideas
    0.22
     initial
    0.21
    Activations Density 0.054%

    No Known Activations