© 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. 84017
    Prev
    Next
    INDEX
    Explanations

    elements related to culture and experiences, particularly in a European context

    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
    adla
    -0.07
     recent
    -0.06
    ato
    -0.06
     Strict
    -0.06
     ar
    -0.06
    latest
    -0.06
    ivÄĽ
    -0.06
    amina
    -0.06
    anj
    -0.06
     latest
    -0.06
    POSITIVE LOGITS
    adians
    0.08
     Americans
    0.08
     American
    0.08
     foreigners
    0.07
     unfamiliar
    0.07
    .useState
    0.07
     FileMode
    0.07
    culture
    0.07
     everywhere
    0.07
     abroad
    0.06
    Activations Density 0.022%

    No Known Activations