© 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. 24740
    Prev
    Next
    INDEX
    Explanations

    expressions related to wealth accumulation and financial transactions

    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
    fault
    -0.17
    Fault
    -0.17
     Feld
    -0.16
     Fault
    -0.16
     FIFO
    -0.15
    Filled
    -0.15
     Fixture
    -0.15
     factorial
    -0.15
    oji
    -0.15
    DEX
    -0.14
    POSITIVE LOGITS
     Fort
    0.49
    Fort
    0.46
     fort
    0.45
    -f
    0.42
    fort
    0.40
     fortune
    0.34
    ort
    0.30
    fortune
    0.30
     forts
    0.29
    -F
    0.29
    Activations Density 0.007%

    No Known Activations