© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 30557
    Prev
    Next
    INDEX
    Explanations

    phrases indicating requests or inquiries

    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
    OVE
    -0.16
     tell
    -0.15
     distinct
    -0.15
    arias
    -0.15
    ivil
    -0.15
    asto
    -0.15
    akit
    -0.15
     Hello
    -0.14
    ovan
    -0.14
    119
    -0.14
    POSITIVE LOGITS
     borrow
    0.24
    borrow
    0.19
     bor
    0.18
     Borrow
    0.18
     Trouble
    0.18
     borrowing
    0.18
     Interest
    0.18
     trouble
    0.17
     interest
    0.17
    Trou
    0.16
    Activations Density 0.013%

    No Known Activations