© 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. 62921
    Prev
    Next
    INDEX
    Explanations

    occurrences of transactions and purchasing-related terms

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     earning
    -0.07
    altar
    -0.07
     earned
    -0.06
    aland
    -0.06
    ulo
    -0.06
    vÄĽd
    -0.06
     fac
    -0.06
    à¸ĵà¸ij
    -0.06
    inki
    -0.06
     uncon
    -0.06
    POSITIVE LOGITS
     online
    0.11
    -online
    0.11
     Online
    0.09
    online
    0.09
    Online
    0.09
     ONLINE
    0.08
    _online
    0.08
     via
    0.08
    439
    0.08
     à¤ijनल
    0.07
    Activations Density 0.012%

    No Known Activations