© 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. 13896
    Prev
    Next
    INDEX
    Explanations

    references to specific national events and historical milestones

    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
     come
    -0.46
     Come
    -0.40
    Come
    -0.38
    come
    -0.36
     spring
    -0.31
    æĺ¥
    -0.29
     Spring
    -0.28
     æĺ¥
    -0.27
    April
    -0.26
    spring
    -0.25
    POSITIVE LOGITS
     August
    0.74
     Aug
    0.73
    August
    0.72
    Aug
    0.68
    -Aug
    0.64
     AUG
    0.64
    aug
    0.58
     aug
    0.57
    _aug
    0.54
     augmentation
    0.53
    Activations Density 0.029%

    No Known Activations