© 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. 33122
    Prev
    Next
    INDEX
    Explanations

    terms related to portion sizes and specifications in food-related contexts

    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
    hem
    -0.15
    RowAtIndexPath
    -0.14
     Nich
    -0.13
     èIJ¬
    -0.12
    ignty
    -0.12
     Spectrum
    -0.12
    aky
    -0.12
    rie
    -0.12
    avy
    -0.12
    oday
    -0.12
    POSITIVE LOGITS
     size
    1.04
    size
    0.88
     sizes
    0.84
     Size
    0.84
    -size
    0.80
    Size
    0.78
    .size
    0.76
    _size
    0.75
     SIZE
    0.72
     sized
    0.68
    Activations Density 0.051%

    No Known Activations