© 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. 83672
    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
    Çİ
    -0.06
    ardo
    -0.06
    anzi
    -0.06
    IQ
    -0.06
    >window
    -0.06
    ढ
    -0.06
     mischief
    -0.06
    avad
    -0.05
    awk
    -0.05
    enia
    -0.05
    POSITIVE LOGITS
    isto
    0.08
    lopen
    0.07
    peria
    0.07
     ÑĦÑĸн
    0.07
     Finnish
    0.07
    ÑĢаз
    0.07
     Helsinki
    0.07
    oft
    0.07
    inne
    0.06
     POSSIBILITY
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.