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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 43189
    Prev
    Next
    INDEX
    Explanations

    the phrase "thing" used in various contexts, indicating its overall significance in the text

    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
    adolu
    -0.16
    ýn
    -0.15
    emoc
    -0.15
    rollo
    -0.15
     μην
    -0.15
    combe
    -0.15
    usercontent
    -0.14
    ÄĽk
    -0.14
    žel
    -0.14
    chw
    -0.14
    POSITIVE LOGITS
    ummy
    0.30
    y
    0.26
    ies
    0.24
    am
    0.23
    ummies
    0.22
    ie
    0.22
    um
    0.20
    amy
    0.20
    /person
    0.19
    iest
    0.19
    Activations Density 0.022%

    No Known Activations