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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12942
    Prev
    Next
    INDEX
    Explanations

    sensory experiences and descriptions related to physical sensations, especially those associated with surgery or anesthesia

    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
    anki
    -0.17
    uÃŃ
    -0.14
     vom
    -0.14
     Infect
    -0.14
     tie
    -0.14
     narrower
    -0.13
     expressive
    -0.13
    à¹Ģศ
    -0.13
    adge
    -0.13
    utin
    -0.13
    POSITIVE LOGITS
     sensation
    0.44
     sensations
    0.42
     feeling
    0.30
     numb
    0.28
     discomfort
    0.26
     feelings
    0.25
     burning
    0.24
     Feeling
    0.24
    Feel
    0.24
     Sens
    0.24
    Activations Density 0.034%

    No Known Activations