© 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. 9180
    Prev
    Next
    INDEX
    Explanations

    references to product sales and distribution metrics

    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
    .scalablytyped
    -0.23
    iferay
    -0.15
    plib
    -0.15
    ofire
    -0.15
    emma
    -0.14
    ÏĦοκ
    -0.14
    oteca
    -0.14
    ç«ĭãģ¦
    -0.14
    olib
    -0.14
    igraphy
    -0.13
    POSITIVE LOGITS
     sold
    0.49
    sold
    0.38
     Sold
    0.37
     SOLD
    0.34
     sell
    0.33
    Sold
    0.32
    _sold
    0.30
     sales
    0.28
     sale
    0.28
     shipped
    0.28
    Activations Density 0.038%

    No Known Activations