© 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. 71632
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ean
    -0.07
     Gors
    -0.06
    ovo
    -0.06
     controversies
    -0.06
    λοÏį
    -0.06
    sic
    -0.06
    arsing
    -0.06
    елен
    -0.06
    mit
    -0.06
    ç·
    -0.05
    POSITIVE LOGITS
    iolet
    0.08
    æij
    0.07
    untime
    0.07
     Tento
    0.07
    sans
    0.07
    ãģķãĤī
    0.07
     Dün
    0.07
     kê
    0.07
     dele
    0.07
    (SS
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.