© 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. 15357
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" in various 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
    imest
    -0.16
    .setViewport
    -0.15
    illin
    -0.15
    .VisualBasic
    -0.14
    ãģŃ
    -0.14
    (TM
    -0.14
    arest
    -0.13
    ãģªãģĮ
    -0.13
    yw
    -0.13
    erez
    -0.13
    POSITIVE LOGITS
     following
    1.22
    following
    1.00
     Following
    0.97
    Following
    0.90
     siguiente
    0.81
     ÑģледÑĥÑİÑī
    0.77
     seguint
    0.77
     siguientes
    0.77
     suiv
    0.72
     next
    0.69
    Activations Density 0.048%

    No Known Activations