© 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. 119659
    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
    âĢİ
    -0.07
     Fuck
    -0.06
    å¹¹ç·ļ
    -0.06
    uvre
    -0.06
    è¨
    -0.06
     Gentle
    -0.06
     critical
    -0.06
     colleague
    -0.06
     anonymous
    -0.06
     maintain
    -0.06
    POSITIVE LOGITS
    iek
    0.08
    hlas
    0.08
    mie
    0.07
    unger
    0.07
    Äħż
    0.07
    esan
    0.07
    psilon
    0.07
    ebra
    0.07
    ÑĢÑĥÑĪ
    0.07
    elon
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.