© 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. 120037
    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
     count
    -0.06
    ade
    -0.06
     superv
    -0.06
    ÙĪرة
    -0.06
     readiness
    -0.06
     good
    -0.06
     overnight
    -0.06
     rank
    -0.06
     ranks
    -0.06
     mente
    -0.06
    POSITIVE LOGITS
    _MetaData
    0.08
    erli
    0.08
    iesen
    0.08
    uitka
    0.08
     Rouge
    0.08
     Blasio
    0.07
    GST
    0.07
    imson
    0.07
    entionPolicy
    0.07
     privile
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.