© 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. 87049
    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
    rish
    -0.07
     amongst
    -0.06
     Newspaper
    -0.06
     preferring
    -0.06
    ux
    -0.06
    ãģĤãģĴ
    -0.06
    appa
    -0.06
     Very
    -0.06
    ãģĿãģĨãģª
    -0.06
     whilst
    -0.05
    POSITIVE LOGITS
    ugo
    0.07
     Contents
    0.07
    Ĺ
    0.06
    _contents
    0.06
    óż
    0.06
     Ragnar
    0.06
     âĸ²
    0.06
    contents
    0.06
    yen
    0.06
     contents
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.