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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 57499
    Prev
    Next
    INDEX
    Explanations

    references to cultural comparisons and parenting styles

    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
    unya
    -0.08
    PÅĻÃŃ
    -0.08
    erald
    -0.08
    Xem
    -0.07
    omik
    -0.07
    بÙĪاسطة
    -0.07
    èģ
    -0.07
    oday
    -0.07
    iek
    -0.07
    enef
    -0.06
    POSITIVE LOGITS
     culture
    0.08
     cultural
    0.08
    culture
    0.07
     nation
    0.07
     Culture
    0.07
    fatal
    0.07
    ffi
    0.07
     famously
    0.06
     fatal
    0.06
     country
    0.06
    Activations Density 0.093%

    No Known Activations