© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 103987
    Prev
    Next
    INDEX
    Explanations

    financial terms related to currency and transactions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    etros
    -0.07
    ipl
    -0.07
    amina
    -0.07
    odata
    -0.07
    ipline
    -0.07
     suất
    -0.07
    ampo
    -0.07
    udiant
    -0.07
    cargo
    -0.06
    ousse
    -0.06
    POSITIVE LOGITS
     coin
    0.09
     denomin
    0.09
    coin
    0.08
    Coin
    0.08
     denomination
    0.08
     coins
    0.08
     Coin
    0.08
    Coins
    0.07
     Coins
    0.07
     bills
    0.07
    Activations Density 0.010%

    No Known Activations