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

    Neuronpedia

    Jacobian LensNEW
    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. 87521
    Prev
    Next
    INDEX
    Explanations

    numerical and statistical data related to geographical areas

    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
    Ãło
    -0.07
    voices
    -0.07
    år
    -0.06
    InView
    -0.06
    opolitan
    -0.06
    earn
    -0.06
    TickCount
    -0.06
    証
    -0.06
    ниÑĤи
    -0.06
    vek
    -0.06
    POSITIVE LOGITS
     surface
    0.08
     land
    0.07
    ihan
    0.07
    surface
    0.07
     Surface
    0.07
    ales
    0.07
    sty
    0.06
    ë¦¬ë¡ľ
    0.06
     bá»ģ
    0.06
     Lap
    0.06
    Activations Density 0.003%

    No Known Activations