© 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. 85911
    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
    xd
    -0.06
     qualities
    -0.06
    acking
    -0.06
    issance
    -0.06
     Opinion
    -0.06
    ionic
    -0.06
    rices
    -0.06
    aqu
    -0.06
    asia
    -0.06
    iper
    -0.05
    POSITIVE LOGITS
    å±ĭ
    0.07
    754
    0.07
    ë£Į
    0.07
     vÃŃde
    0.07
    Chip
    0.07
    Ð®ÐĽ
    0.07
    textTheme
    0.06
    icode
    0.06
    emens
    0.06
    _reload
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.