© 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. 23950
    Prev
    Next
    INDEX
    Explanations

    instances of high numerical values or comparisons

    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
    urette
    -0.15
    krv
    -0.15
     Infragistics
    -0.14
    -FIRST
    -0.14
    okud
    -0.14
    سÙĪب
    -0.14
    iage
    -0.13
    ederland
    -0.13
    peare
    -0.13
    ÄIJT
    -0.13
    POSITIVE LOGITS
     Siri
    0.14
    0.14
     Saf
    0.13
    lag
    0.13
    елов
    0.13
    ir
    0.12
     Waters
    0.12
    rap
    0.12
     Mission
    0.12
    isk
    0.12
    Activations Density 0.044%

    No Known Activations