© 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 EvalsExportsAPI 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. 14205
    Prev
    Next
    INDEX
    Explanations

    references to copies or variations of products, particularly in relation to games or vehicles

    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
    argest
    -0.18
    arest
    -0.15
    ictim
    -0.14
    å·»
    -0.14
    adb
    -0.14
    XB
    -0.14
    linger
    -0.13
     richness
    -0.13
    exter
    -0.13
    ìĤ¬ìĹħ
    -0.13
    POSITIVE LOGITS
     variants
    0.56
     variant
    0.55
     variations
    0.52
     variation
    0.49
     versions
    0.45
     Variant
    0.44
     version
    0.43
     Variation
    0.41
    Variant
    0.40
    variant
    0.39
    Activations Density 0.080%

    No Known Activations