© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 54983
    Prev
    Next
    INDEX
    Explanations

    business-related terminology and details about product availability

    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
    ÙĬرا
    -0.15
     chips
    -0.15
    oppins
    -0.15
    asje
    -0.14
     MANAGEMENT
    -0.14
    andalone
    -0.14
     clothes
    -0.14
    transport
    -0.14
    ownership
    -0.14
     NDEBUG
    -0.13
    POSITIVE LOGITS
     supplier
    0.18
     company
    0.18
     accessory
    0.18
     distrib
    0.18
     Parts
    0.17
     redistrib
    0.17
     Company
    0.16
    pany
    0.16
     Distrib
    0.16
    Parts
    0.16
    Activations Density 0.045%

    No Known Activations