© 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 EvalsExportsAPI 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. 14422
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" and sentences that begin with a specific formatting or punctuation

    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
    她们
    -0.37
    å®ĥ们
    -0.29
     they
    -0.28
     their
    -0.27
    they
    -0.25
     theirs
    -0.23
    their
    -0.22
     Their
    -0.22
    Their
    -0.21
     оно
    -0.21
    POSITIVE LOGITS
     himself
    0.49
     him
    0.47
     his
    0.45
     he
    0.42
    ä»ĸ
    0.39
    his
    0.38
    ä»ĸçļĦ
    0.35
     lui
    0.33
    him
    0.33
    ï¼Įä»ĸ
    0.33
    Activations Density 0.000%

    No Known Activations