© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 63185
    Prev
    Next
    INDEX
    Explanations

    words related to significant events or celebrations

    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
    =__
    -0.16
    _TYP
    -0.16
    aily
    -0.15
     Saturdays
    -0.14
    irs
    -0.14
    407
    -0.13
    [sizeof
    -0.13
    LIKELY
    -0.13
    ORIZONTAL
    -0.13
    Corner
    -0.13
    POSITIVE LOGITS
     National
    0.35
     International
    0.32
    National
    0.30
     World
    0.28
    International
    0.27
    World
    0.22
     NATIONAL
    0.21
     Arbor
    0.20
    .World
    0.20
    -national
    0.20
    Activations Density 0.041%

    No Known Activations