© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 94597
    Prev
    Next
    INDEX
    Explanations

    specific strains of the influenza virus and their characteristics

    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
    .scalablytyped
    -0.09
    peria
    -0.07
     Colony
    -0.06
    oup
    -0.06
    oku
    -0.06
    #
    -0.06
    DSA
    -0.06
    Ļ¨
    -0.06
    licht
    -0.06
    endi
    -0.06
    POSITIVE LOGITS
     subtype
    0.07
    resher
    0.07
    .gb
    0.06
     Cho
    0.06
    .partial
    0.06
     гÑĢи
    0.06
     cru
    0.06
     variant
    0.06
     cho
    0.06
    ови
    0.06
    Activations Density 0.004%

    No Known Activations