© 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. 15-LLAMASCOPE-RES-131K
    11. 104366
    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
    agne
    -0.07
    annis
    -0.07
    ugin
    -0.07
    annes
    -0.07
    apeutics
    -0.06
    thing
    -0.06
    htub
    -0.06
    riot
    -0.06
    rchive
    -0.06
    uje
    -0.06
    POSITIVE LOGITS
    گاÙĨ
    0.07
    altimore
    0.07
    cke
    0.07
    ï¼ļ↵
    0.06
    Displays
    0.06
    ॰
    0.06
    еÑĢеж
    0.06
    جÙĪ
    0.06
    há
    0.06
     åıĬ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.