© 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. 28562
    Prev
    Next
    INDEX
    Explanations

    instances of the term "ol" 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
    esis
    -0.21
    i
    -0.20
    ed
    -0.20
    o
    -0.18
    ess
    -0.18
    es
    -0.17
    e
    -0.17
    esse
    -0.17
    eded
    -0.16
    eel
    -0.16
    POSITIVE LOGITS
    ateral
    0.18
    llll
    0.18
    gia
    0.18
    phe
    0.17
    omb
    0.17
    ERA
    0.17
    lius
    0.17
    monary
    0.16
    tx
    0.16
    lege
    0.16
    Activations Density 0.024%

    No Known Activations