© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 40734
    Prev
    Next
    INDEX
    Explanations

    the prefix "un-" indicating negation or opposition

    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
    actively
    -0.18
    éĽĦ
    -0.16
    arton
    -0.15
    å²³
    -0.15
    disposed
    -0.15
    ège
    -0.14
    inand
    -0.14
    owie
    -0.14
    .setter
    -0.14
    964
    -0.14
    POSITIVE LOGITS
     sustainable
    0.20
    -American
    0.16
    help
    0.16
    mask
    0.16
     healthy
    0.16
    bridge
    0.16
    wise
    0.16
     fair
    0.16
    nn
    0.15
    nen
    0.15
    Activations Density 0.028%

    No Known Activations