© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 41341
    Prev
    Next
    INDEX
    Explanations

    references to purity, home, the web, and saturation levels

    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
    ,...↵↵
    -0.14
     BoxFit
    -0.14
    readcr
    -0.14
    tml
    -0.14
    slt
    -0.14
     trú
    -0.13
    ئ
    -0.13
    uxt
    -0.13
    unable
    -0.12
    ä½µ
    -0.12
    POSITIVE LOGITS
    inos
    0.15
    âĢĮâĢĮ
    0.14
    زة
    0.13
    .UIManager
    0.13
    ãĥ³ãĤ°
    0.13
    ожеÑĤ
    0.13
    isha
    0.12
    red
    0.12
    Âł
    0.12
    arel
    0.12
    Activations Density 0.046%

    No Known Activations