© 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. 79030
    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
    .Apis
    -0.07
    (loader
    -0.07
    steller
    -0.07
    leÅŁik
    -0.07
    शन
    -0.07
    طاÙĤ
    -0.07
    æ¨Ļ
    -0.07
    .Slf
    -0.07
     Seks
    -0.06
    .TestTools
    -0.06
    POSITIVE LOGITS
    ys
    0.07
    825
    0.06
    X
    0.06
    is
    0.06
    aucoup
    0.06
    0.06
    –
    0.06
    agi
    0.05
    abb
    0.05
     kiss
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.