© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 40659
    Prev
    Next
    INDEX
    Explanations

    references to monetary amounts

    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
    d
    -0.38
    c
    -0.37
    e
    -0.36
    p
    -0.33
    u
    -0.33
    t
    -0.32
    a
    -0.32
    i
    -0.31
    b
    -0.29
    y
    -0.29
    POSITIVE LOGITS
    illion
    0.18
    ï¸ı
    0.17
    sez
    0.17
    contri
    0.16
    spir
    0.16
    ilion
    0.16
    reon
    0.16
    ndl
    0.16
    dependent
    0.15
    clus
    0.15
    Activations Density 0.238%

    No Known Activations