© 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. 15-LLAMASCOPE-RES-131K
    11. 61944
    Prev
    Next
    INDEX
    Explanations

    references to live events and community engagement, particularly in the context of advocacy and social justice organizations

    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
    aris
    -0.09
    familia
    -0.07
    oon
    -0.07
    辺
    -0.07
    ologne
    -0.07
    ẹn
    -0.07
    astle
    -0.07
    ERICA
    -0.07
     поÑģк
    -0.07
    rike
    -0.07
    POSITIVE LOGITS
     supplement
    0.06
     Circular
    0.06
    (TIM
    0.06
     brand
    0.06
     anonymously
    0.06
    brand
    0.06
     act
    0.06
     Supreme
    0.06
    CH
    0.06
    eneric
    0.06
    Activations Density 0.018%

    No Known Activations