© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 29375
    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
     discrepan
    -0.08
    ÑĢо
    -0.07
    SDK
    -0.07
    592
    -0.06
    _mk
    -0.06
    835
    -0.06
    éłĵ
    -0.06
     strav
    -0.06
    copies
    -0.06
    conomics
    -0.06
    POSITIVE LOGITS
    ught
    0.07
     wording
    0.07
    enz
    0.06
     underlying
    0.06
    filer
    0.06
     _
    0.06
    ezier
    0.06
     Guid
    0.06
     Trend
    0.06
    ugu
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.