© 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. 22688
    Prev
    Next
    INDEX
    Explanations

    terms related to significant financial sums and wealth

    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
    üml
    -0.18
    criptor
    -0.16
    dued
    -0.16
    bic
    -0.15
     rá»Ļng
    -0.14
    .Interop
    -0.14
    disposing
    -0.14
    μÏĢο
    -0.14
     kı
    -0.13
    rypton
    -0.13
    POSITIVE LOGITS
     sum
    0.46
     sums
    0.45
    sum
    0.36
    -sum
    0.34
     Sum
    0.32
     suma
    0.30
    Sum
    0.29
    (sum
    0.27
    _sum
    0.26
    .sum
    0.26
    Activations Density 0.040%

    No Known Activations