© 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. 127274
    Prev
    Next
    INDEX
    Explanations

    statements about athletic performance and potential

    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
    (æ°´
    -0.07
    ueue
    -0.07
    ãģ°ãģĭãĤĬ
    -0.07
    Temporary
    -0.07
    renom
    -0.06
    gua
    -0.06
    MediaType
    -0.06
    recent
    -0.06
     ÙĪضع
    -0.06
    LOUD
    -0.06
    POSITIVE LOGITS
     eventual
    0.07
     future
    0.07
    yth
    0.07
     eventually
    0.07
    æĪIJ人
    0.07
     development
    0.06
    lef
    0.06
     tomorrow
    0.06
     Eventually
    0.06
    ellen
    0.06
    Activations Density 0.013%

    No Known Activations