© 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. 9045
    Prev
    Next
    INDEX
    Explanations

    words related to names or proper nouns

    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
    e
    -0.40
    y
    -0.31
    ness
    -0.31
    c
    -0.28
    l
    -0.24
    ea
    -0.23
    m
    -0.23
    se
    -0.23
    eum
    -0.23
    x
    -0.23
    POSITIVE LOGITS
    iado
    0.20
    iou
    0.19
    gee
    0.18
    ÑģÑı
    0.17
    books
    0.17
    urope
    0.17
    ÑĦиÑĨи
    0.17
    enticated
    0.17
    iras
    0.17
    velopment
    0.17
    Activations Density 0.054%

    No Known Activations