© 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. 13356
    Prev
    Next
    INDEX
    Explanations

    the presence of quotation marks indicating spoken dialogue

    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
    s
    -0.69
    Ùĩ
    -0.39
    a
    -0.32
    ska
    -0.28
    sburg
    -0.28
    ÏĤ
    -0.24
    sian
    -0.24
    sand
    -0.23
    à¸Ĺ
    -0.22
     "
    -0.22
    POSITIVE LOGITS
    OGLE
    0.17
    -prepend
    0.16
    ratulations
    0.16
    odore
    0.15
    ":[{↵
    0.15
    zeÅĪ
    0.15
    atre
    0.15
    gli
    0.14
    referrer
    0.14
     же
    0.13
    Activations Density 0.444%

    No Known Activations