© 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. 41323
    Prev
    Next
    INDEX
    Explanations

    names of individuals, specifically surnames or last names

    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
    setFlash
    -0.15
    archs
    -0.15
    kiye
    -0.15
    iversit
    -0.15
    gons
    -0.15
    Ñĩки
    -0.15
    vetica
    -0.14
     tôn
    -0.14
    abeth
    -0.14
    ackers
    -0.14
    POSITIVE LOGITS
    eck
    0.18
    ibus
    0.16
    eyer
    0.15
    öyle
    0.15
    atis
    0.14
    erville
    0.14
    ocab
    0.14
    опÑĢи
    0.14
    DT
    0.13
    αι
    0.13
    Activations Density 0.015%

    No Known Activations