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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 84762
    Prev
    Next
    INDEX
    Explanations

    statistics and figures related to water access and sanitation issues

    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
    umatic
    -0.07
    uzzi
    -0.07
     Zheng
    -0.06
    uling
    -0.06
    jours
    -0.06
     ÄijÆ¡n
    -0.06
    .Debugger
    -0.06
    vip
    -0.06
    мÑı
    -0.06
    endez
    -0.06
    POSITIVE LOGITS
     lack
    0.07
     poverty
    0.06
    591
    0.06
     typical
    0.06
     Cop
    0.06
    lack
    0.06
     lacks
    0.06
    MS
    0.06
    æĵį
    0.06
     villagers
    0.06
    Activations Density 0.062%

    No Known Activations