© 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. 78018
    Prev
    Next
    INDEX
    Explanations

    references to sports events and competitions

    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
    resco
    -0.08
    leck
    -0.08
    ankan
    -0.08
    ông
    -0.07
    raphics
    -0.07
    çĥĪ
    -0.07
    .opensource
    -0.07
    usto
    -0.07
    erm
    -0.07
    roperties
    -0.07
    POSITIVE LOGITS
     soccer
    0.07
    inis
    0.06
    anou
    0.06
    chet
    0.06
     sne
    0.06
     England
    0.05
     Game
    0.05
    uppe
    0.05
     pressure
    0.05
     bomb
    0.05
    Activations Density 0.001%

    No Known Activations