© 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. 63623
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize connection or relationships

    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
    ä¹Ī
    -0.14
    ibel
    -0.14
    ãĥ¼ãĥĢ
    -0.14
     -----------------------------------------------------------------------------↵
    -0.14
    ÑĢÑĸз
    -0.14
     бокÑĥ
    -0.14
    mour
    -0.13
    eyse
    -0.13
    _tF
    -0.13
    жÑĥ
    -0.13
    POSITIVE LOGITS
    /am
    0.27
     sexes
    0.23
     two
    0.23
    zeit
    0.22
     them
    0.21
     اÙĦÙħÙĦÙĦÛĮ
    0.20
     innings
    0.18
    âĢĮاÙĦÙħÙĦÙĦÛĮ
    0.18
     genders
    0.18
     now
    0.18
    Activations Density 0.047%

    No Known Activations