© 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. 42679
    Prev
    Next
    INDEX
    Explanations

    words or phrases that suggest significant events or changes

    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
    âĢ¦and
    -0.14
    èĥ½å¤Ł
    -0.14
     Fucking
    -0.13
    Ì
    -0.13
    -0.13
    uilder
    -0.13
     recieved
    -0.12
     fucking
    -0.12
     bour
    -0.12
     jewish
    -0.12
    POSITIVE LOGITS
    ëį°ìĿ´íĬ¸
    0.17
     pronto
    0.14
    ort
    0.14
    ãģ°ãģĭãĤĬ
    0.14
    .openConnection
    0.13
     надо
    0.13
    âĸ²
    0.13
    -fontawesome
    0.13
     vistas
    0.13
    <decltype
    0.12
    Activations Density 0.009%

    No Known Activations