© 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 EvalsExportsinterp-engineNEWAPI 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. 12608
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the."

    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
    //{{
    -0.18
    #af
    -0.15
    #ab
    -0.15
    _lite
    -0.15
    ElementException
    -0.14
    mitter
    -0.14
    .IsNullOr
    -0.13
    afe
    -0.13
    ï¼ģï¼ģ↵↵
    -0.13
    ibName
    -0.13
    POSITIVE LOGITS
     following
    0.18
    following
    0.17
    issant
    0.15
    ikut
    0.15
     Following
    0.15
    idd
    0.14
    110
    0.14
     cui
    0.14
     focus
    0.14
     chances
    0.14
    Activations Density 0.036%

    No Known Activations