© 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 EvalsExportsAPI 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. 78339
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms related to health and medical conditions

    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
    plevel
    -0.08
    serter
    -0.07
    È
    -0.07
     ÄĮes
    -0.07
    ROID
    -0.07
    ÑĢаÑĩ
    -0.07
    haul
    -0.06
    orra
    -0.06
    ency
    -0.06
    hift
    -0.06
    POSITIVE LOGITS
    etheless
    0.09
    adays
    0.08
    odore
    0.07
    ÑįÑĤомÑĥ
    0.07
    aret
    0.07
    jamin
    0.07
    achusetts
    0.06
    apolis
    0.06
    /-
    0.06
    alyze
    0.06
    Activations Density 0.025%

    No Known Activations