© 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. 89216
    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
    .Compute
    -0.07
    Verdana
    -0.07
    Segoe
    -0.07
    Calibri
    -0.07
    ¥IJ
    -0.06
    çij
    -0.06
    анк
    -0.06
    CurrentValue
    -0.06
    estre
    -0.06
     तर
    -0.06
    POSITIVE LOGITS
     our
    0.13
     ourselves
    0.11
    our
    0.11
     ours
    0.07
     OUR
    0.07
    ons
    0.07
    æĪij们çļĦ
    0.07
     already
    0.07
     Already
    0.07
     unsere
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.