© 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. 42327
    Prev
    Next
    INDEX
    Explanations

    statistical correlations related to family, religion, and demographics in the context of LGBT youth and their treatment

    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
    issen
    -0.17
    ิà¸Ļà¸Ĺร
    -0.15
    å²
    -0.15
    atten
    -0.15
    unal
    -0.15
    ves
    -0.14
     Spor
    -0.14
    dde
    -0.14
    XM
    -0.14
    à¸ŀà¸Ń
    -0.14
    POSITIVE LOGITS
     more
    0.49
     less
    0.37
    more
    0.35
     lik
    0.34
     MORE
    0.34
     twice
    0.33
     più
    0.32
     más
    0.31
     More
    0.31
    More
    0.30
    Activations Density 0.053%

    No Known Activations