© 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. 125117
    Prev
    Next
    INDEX
    Explanations

    references to competitive cycling stages and events

    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
    pole
    -0.06
    BindingUtil
    -0.06
    lyn
    -0.06
    InParameter
    -0.06
     rap
    -0.06
    iteur
    -0.06
    airro
    -0.06
    aliz
    -0.06
    tolower
    -0.06
    AIT
    -0.06
    POSITIVE LOGITS
     route
    0.09
     Route
    0.09
    route
    0.08
    Route
    0.07
     Tour
    0.07
    /routes
    0.07
    .route
    0.07
    ROUTE
    0.07
     Bols
    0.06
     routes
    0.06
    Activations Density 0.014%

    No Known Activations