© 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. 118294
    Prev
    Next
    INDEX
    Explanations

    references to countries or national affiliations in the context of sports

    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
    StrictEqual
    -0.07
    TEGER
    -0.07
    -Clause
    -0.07
    pras
    -0.07
    printStats
    -0.07
    ä¹Ī
    -0.07
    odic
    -0.06
    rosso
    -0.06
    Conexion
    -0.06
    _UNUSED
    -0.06
    POSITIVE LOGITS
     tem
    0.07
    attr
    0.06
    oker
    0.06
    /meta
    0.06
    tem
    0.06
    letcher
    0.06
    mer
    0.06
    IME
    0.06
    peak
    0.05
    ког
    0.05
    Activations Density 0.002%

    No Known Activations