© 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. 88291
    Prev
    Next
    INDEX
    Explanations

    references to scientific societies focused on virology

    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
    è©
    -0.07
    zen
    -0.07
     Grande
    -0.06
    velt
    -0.06
    olid
    -0.06
    اساÙĨ
    -0.06
     fri
    -0.06
    .bukkit
    -0.06
     mindset
    -0.06
    anvas
    -0.06
    POSITIVE LOGITS
    Statics
    0.07
    .SwingConstants
    0.07
    ëĦ·
    0.06
     crafts
    0.06
    orz
    0.06
     oui
    0.06
    ade
    0.06
     tÃŃn
    0.06
    ubb
    0.06
     Crafts
    0.06
    Activations Density 0.006%

    No Known Activations