© 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. 125752
    Prev
    Next
    INDEX
    Explanations

    references to football leagues, specifically La Liga

    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
    nte
    -0.07
     Hus
    -0.07
    ocrat
    -0.07
    itches
    -0.07
    bourg
    -0.06
    itag
    -0.06
    ity
    -0.06
    CHAN
    -0.06
     polar
    -0.06
    uty
    -0.06
    POSITIVE LOGITS
    mpz
    0.06
    istring
    0.06
    iard
    0.06
    zig
    0.06
    AVED
    0.06
    鹿
    0.06
    hare
    0.06
    çķ
    0.06
    serve
    0.06
    çª
    0.06
    Activations Density 0.001%

    No Known Activations