© 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. 43713
    Prev
    Next
    INDEX
    Explanations

    terms related to online promotion and bundling strategies

    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
     Lal
    -0.18
    æ½
    -0.17
    er
    -0.16
    erin
    -0.15
    κι
    -0.15
    çŃĴ
    -0.15
    ç§Ģ
    -0.15
    pond
    -0.14
    رÙĪØ´
    -0.14
    ERENCE
    -0.14
    POSITIVE LOGITS
    les
    0.54
    led
    0.54
    ling
    0.48
    ler
    0.43
    lers
    0.40
    LES
    0.39
    lesh
    0.34
    lem
    0.31
    let
    0.30
    LED
    0.30
    Activations Density 0.022%

    No Known Activations