© 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. 24305
    Prev
    Next
    INDEX
    Explanations

    monetary values in the context of large sums of money

    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
    cott
    -0.15
    iqueta
    -0.15
    otec
    -0.15
    ì¹ľ
    -0.15
    bject
    -0.14
    lec
    -0.14
    allas
    -0.14
    à¹ĥà¸Ī
    -0.13
    ted
    -0.13
    eph
    -0.13
    POSITIVE LOGITS
     of
    0.30
    -of
    0.24
    OfWork
    0.22
     upon
    0.22
    RuleContext
    0.20
    _of
    0.20
     Of
    0.18
     Upon
    0.17
    Upon
    0.17
    .of
    0.17
    Activations Density 0.026%

    No Known Activations