© 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. 9-LLAMASCOPE-RES-131K
    11. 93963
    Prev
    Next
    INDEX
    Explanations

    concepts related to taxation and financial 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
    SizeMode
    -0.07
    efe
    -0.07
     vé
    -0.06
    .execution
    -0.06
    à¹īà¸Ńม
    -0.06
     plaint
    -0.06
     Bench
    -0.06
    okol
    -0.06
     dataSize
    -0.06
     اÙĦدÙĪÙĦÙĬ
    -0.06
    POSITIVE LOGITS
    584
    0.07
    ucken
    0.07
    osten
    0.07
    è¿Ļæł·çļĦ
    0.06
     Kov
    0.06
    icken
    0.06
    edList
    0.06
     رز
    0.06
     dev
    0.06
     nickel
    0.06
    Activations Density 0.061%

    No Known Activations