© 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. 40935
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Ehud," particularly in relation to significant events or contexts

    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
    -0.17
    ignon
    -0.16
    amente
    -0.16
    eon
    -0.16
    Neo
    -0.15
    ein
    -0.15
     dash
    -0.14
    ways
    -0.14
    way
    -0.14
     Rank
    -0.14
    POSITIVE LOGITS
    avior
    0.21
    lers
    0.18
    entai
    0.18
    ovah
    0.16
    ockey
    0.16
    ylene
    0.16
    aviour
    0.15
    udit
    0.15
    ud
    0.15
    anced
    0.15
    Activations Density 0.004%

    No Known Activations