© 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 EvalsExportsinterp-engineNEWAPI 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. 120595
    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
    mouseleave
    -0.07
    _MT
    -0.06
    eniable
    -0.06
    é¦Ļ
    -0.06
     Nearly
    -0.06
    ë²Į
    -0.06
    pring
    -0.06
    paragus
    -0.06
    iese
    -0.06
    rah
    -0.06
    POSITIVE LOGITS
    uç
    0.06
     âĢ«
    0.06
    ×Ĺ
    0.06
    ×IJ
    0.06
    urrent
    0.06
    esser
    0.06
    ×Ļ×
    0.06
    ãģĮãģĬ
    0.06
    سÙĪب
    0.06
    610
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.