© 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. 13955
    Prev
    Next
    INDEX
    Explanations

    references to gifts and special occasions

    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
    ettes
    -0.15
    icker
    -0.15
    ardown
    -0.14
    putc
    -0.14
    ials
    -0.13
    umer
    -0.13
     Sesso
    -0.13
    _IOS
    -0.13
    burgh
    -0.13
    ebek
    -0.13
    POSITIVE LOGITS
     gift
    1.06
     gifts
    0.97
     Gift
    0.90
    gift
    0.89
    Gift
    0.85
     Gifts
    0.83
    _gift
    0.64
     gifted
    0.62
     presents
    0.48
     gif
    0.42
    Activations Density 0.040%

    No Known Activations