© 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. 42308
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding genetics and intelligence

    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
    βα
    -0.15
     binder
    -0.14
     banquet
    -0.14
     Hick
    -0.13
     Zar
    -0.13
    hsi
    -0.13
     mů
    -0.13
    å±ħ
    -0.13
    ãĤ¤ãĤ¯
    -0.13
     homosex
    -0.13
    POSITIVE LOGITS
     genetic
    0.40
     genes
    0.37
     genetics
    0.36
     Genetic
    0.33
     genetically
    0.32
    gen
    0.31
    Gen
    0.29
     Genetics
    0.29
     gene
    0.29
     trait
    0.28
    Activations Density 0.242%

    No Known Activations