© 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. 129758
    Prev
    Next
    INDEX
    Explanations

    references to sports events and competition

    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
     jugg
    -0.07
    exion
    -0.07
    allo
    -0.07
    åºķ
    -0.06
    andom
    -0.06
    è¿ŀ
    -0.06
    ningen
    -0.06
    insky
    -0.06
    üssen
    -0.06
    nem
    -0.06
    POSITIVE LOGITS
     Distance
    0.10
    Distance
    0.08
     distances
    0.08
     distance
    0.08
    -distance
    0.07
    Finish
    0.07
     Finish
    0.07
    distance
    0.07
     Running
    0.07
     meters
    0.07
    Activations Density 0.009%

    No Known Activations