© 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. 5-LLAMASCOPE-RES-131K
    11. 126691
    Prev
    Next
    INDEX
    Explanations

    mentions of various entertainment-related entities and their associated news or events

    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
    kün
    -0.06
    ICS
    -0.06
    cio
    -0.06
    erm
    -0.06
    ån
    -0.06
    hof
    -0.06
     Agenda
    -0.06
    ovol
    -0.06
    dsn
    -0.05
    aternion
    -0.05
    POSITIVE LOGITS
     Colomb
    0.07
    instein
    0.07
    uss
    0.07
     Morav
    0.07
     spons
    0.06
    _COMPILE
    0.06
    Twig
    0.06
     OTHERWISE
    0.06
    nett
    0.06
     queryInterface
    0.06
    Activations Density 0.001%

    No Known Activations