© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 56039
    Prev
    Next
    INDEX
    Explanations

    references to specific events or competitions in the context of arts or 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
    ema
    -0.07
     bench
    -0.07
     MMA
    -0.06
    EMA
    -0.06
    iox
    -0.06
     Bench
    -0.06
    Cities
    -0.06
    ?key
    -0.06
     suger
    -0.06
    売
    -0.06
    POSITIVE LOGITS
     horses
    0.08
     Equ
    0.08
     Resist
    0.07
     Stable
    0.07
     horse
    0.07
     riders
    0.07
     BST
    0.07
    feed
    0.07
     rider
    0.07
     Caval
    0.07
    Activations Density 0.001%

    No Known Activations