© 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. 41003
    Prev
    Next
    INDEX
    Explanations

    instances of the word "major."

    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
    inia
    -0.20
    ori
    -0.16
     manner
    -0.16
    sb
    -0.16
    MainMenu
    -0.15
    ses
    -0.15
    sen
    -0.14
    ts
    -0.14
    ker
    -0.14
    sled
    -0.14
    POSITIVE LOGITS
    -league
    0.37
    itarian
    0.35
     league
    0.31
    ly
    0.30
    league
    0.29
     League
    0.26
    ity
    0.24
    /min
    0.24
    stay
    0.23
    itary
    0.23
    Activations Density 0.024%

    No Known Activations