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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 37
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and statistical 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
     Weeks
    -0.16
     Week
    -0.16
    Week
    -0.15
    andin
    -0.14
    week
    -0.14
    mÄĽ
    -0.14
    esis
    -0.14
     Dw
    -0.14
    ãĥ³ãĤ°
    -0.14
     Year
    -0.14
    POSITIVE LOGITS
     decades
    0.55
     decade
    0.37
     century
    0.34
    40
    0.32
    30
    0.30
    dec
    0.30
     generation
    0.29
     déc
    0.28
     generations
    0.27
    50
    0.27
    Activations Density 0.089%

    No Known Activations