© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9176
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical sensations or actions related to bodily functions

    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
    iffe
    -0.16
    ecast
    -0.16
     Bow
    -0.15
    лÑĥÑĪ
    -0.15
    Ľ°
    -0.15
     bree
    -0.14
     kvin
    -0.14
    prite
    -0.14
    otal
    -0.14
     Lowe
    -0.13
    POSITIVE LOGITS
     saliva
    0.42
     dro
    0.33
     tongue
    0.30
     Dro
    0.29
    dro
    0.28
     spit
    0.28
     licked
    0.28
     licking
    0.27
     Tong
    0.27
     tongues
    0.27
    Activations Density 0.008%

    No Known Activations