© 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. 16570
    Prev
    Next
    INDEX
    Explanations

    mentions of economic transactions and social dynamics involving communities

    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
    _Ex
    -0.06
    ä¸ĺ
    -0.06
     Mech
    -0.06
    veis
    -0.06
     åİŁ
    -0.06
     exclus
    -0.06
     пеÑĢеÑĤ
    -0.05
    139
    -0.05
     natives
    -0.05
    ÑģилÑĮ
    -0.05
    POSITIVE LOGITS
    ustr
    0.08
     America
    0.08
     these
    0.08
    these
    0.07
    ÙĤاÙħ
    0.07
    476
    0.07
    952
    0.07
    ylie
    0.07
    nech
    0.07
    America
    0.06
    Activations Density 0.027%

    No Known Activations