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. 31412
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" in various contexts

    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
    jedn
    -0.16
    .INSTANCE
    -0.15
     shelf
    -0.15
    ÑĤаб
    -0.15
    effect
    -0.15
    \xff
    -0.14
     efekt
    -0.14
    gether
    -0.14
    ftware
    -0.14
    IENTATION
    -0.14
    POSITIVE LOGITS
     midst
    0.41
     wake
    0.35
     meantime
    0.34
     context
    0.32
    wake
    0.29
     absence
    0.29
     vicinity
    0.29
     guise
    0.27
     case
    0.27
    context
    0.27
    Activations Density 0.148%

    No Known Activations