© 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. 63611
    Prev
    Next
    INDEX
    Explanations

    phrases indicating usability and performance enhancements

    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
     because
    -0.48
    because
    -0.43
     Because
    -0.38
     porque
    -0.36
    Because
    -0.36
    åĽłä¸º
    -0.34
    à¹Ģà¸ŀราะ
    -0.30
    ï¼ĮåĽłä¸º
    -0.29
     but
    -0.28
    ecause
    -0.27
    POSITIVE LOGITS
     overall
    0.18
    even
    0.16
     here
    0.16
     EVEN
    0.16
    overall
    0.15
     even
    0.15
    ĥĿ
    0.14
     Even
    0.14
     territory
    0.14
    Overall
    0.14
    Activations Density 0.002%

    No Known Activations