© 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. 125787
    Prev
    Next
    INDEX
    Explanations

    metrics related to water scarcity and economic rankings

    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
    ãĥŁãĥ¥
    -0.08
    esen
    -0.07
     airs
    -0.07
    ABCDEFG
    -0.07
    IEW
    -0.07
    ICENSE
    -0.07
    ande
    -0.07
    itte
    -0.07
    athi
    -0.07
    миниÑģÑĤÑĢа
    -0.07
    POSITIVE LOGITS
     where
    0.07
     per
    0.07
    where
    0.06
     pace
    0.06
    §è¡Į
    0.06
    ductive
    0.06
     bot
    0.06
     Bot
    0.06
    dat
    0.06
     --
    0.06
    Activations Density 0.022%

    No Known Activations