© 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. 22664
    Prev
    Next
    INDEX
    Explanations

    phrases or actions related to drinking and socializing

    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
     Resource
    -0.14
    ุà¸ķ
    -0.14
    adow
    -0.14
    uels
    -0.14
    erman
    -0.13
    aux
    -0.13
     letter
    -0.13
     Recipe
    -0.13
     Spoon
    -0.13
    azz
    -0.13
    POSITIVE LOGITS
     beers
    0.33
     beer
    0.32
     whiskey
    0.29
     spirits
    0.28
     martin
    0.28
     drinks
    0.27
     gin
    0.27
     ale
    0.26
     rum
    0.26
     Guinness
    0.26
    Activations Density 0.100%

    No Known Activations