© 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. 15711
    Prev
    Next
    INDEX
    Explanations

    phrases that describe performances or displays of talent

    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
    ippi
    -0.07
    antino
    -0.06
    irl
    -0.06
    itta
    -0.06
    owell
    -0.06
     Gust
    -0.06
    ittal
    -0.06
     Platz
    -0.06
     suspension
    -0.06
     Shen
    -0.06
    POSITIVE LOGITS
    isor
    0.07
    performance
    0.07
     effort
    0.07
    plication
    0.07
     val
    0.07
    ÑĢава
    0.07
     performances
    0.07
    ванов
    0.07
     damp
    0.07
    oga
    0.06
    Activations Density 0.015%

    No Known Activations