© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 124598
    Prev
    Next
    INDEX
    Explanations

    abbreviation acronyms related to business and finance

    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
    ̣
    -0.07
     Middleton
    -0.07
    CO
    -0.07
    allback
    -0.07
    esco
    -0.07
    uxtap
    -0.06
     fronts
    -0.06
    bower
    -0.06
    Scheduler
    -0.06
    ìĭľìĹIJ
    -0.06
    POSITIVE LOGITS
    onal
    0.06
    onen
    0.06
    fulness
    0.06
    enie
    0.06
    -cut
    0.06
    ahan
    0.06
    presso
    0.06
    urus
    0.06
    JavaScript
    0.06
    efe
    0.06
    Activations Density 0.043%

    No Known Activations