© 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. 59980
    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
    âĪı
    -0.08
     Feder
    -0.07
    .respond
    -0.07
    .Dot
    -0.07
    ilik
    -0.07
     Jaw
    -0.07
    _macros
    -0.07
    Ñ
    -0.07
    ath
    -0.07
     Hlav
    -0.07
    POSITIVE LOGITS
     now
    0.06
     implementations
    0.06
     Brexit
    0.06
    Graphics
    0.06
     British
    0.06
    coal
    0.06
     coal
    0.06
    eric
    0.06
     Instruments
    0.06
    åIJĦç§į
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.