© 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. 63609
    Prev
    Next
    INDEX
    Explanations

    references to news sources and reporting

    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
     Hampshire
    -0.20
     Wisconsin
    -0.16
     Monad
    -0.16
    دÙĪد
    -0.16
     San
    -0.15
     Richmond
    -0.15
     Staten
    -0.15
     Rae
    -0.15
    asury
    -0.15
     Rutgers
    -0.14
    POSITIVE LOGITS
     Oklahoma
    0.76
     Tulsa
    0.60
     OK
    0.53
     Ok
    0.51
    OK
    0.47
     ok
    0.46
    Ok
    0.45
    .ok
    0.41
    -ok
    0.41
    lahoma
    0.40
    Activations Density 0.019%

    No Known Activations