Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5334
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations related to awards and recognitions in nursing

    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
    istrator
    -0.07
    izzo
    -0.07
    expo
    -0.07
    artner
    -0.07
    धर
    -0.06
    isper
    -0.06
    ocator
    -0.06
    baugh
    -0.06
    ovice
    -0.06
    onom
    -0.06
    POSITIVE LOGITS
    ami
    0.07
    yc
    0.07
    aku
    0.07
    quir
    0.07
    ies
    0.06
    yp
    0.06
    514
    0.06
    ichi
    0.06
    ley
    0.06
    eyin
    0.06
    Activations Density 0.004%

    No Known Activations