© 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. 117308
    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
     amongst
    -0.09
    -esque
    -0.07
     whilst
    -0.07
     Whilst
    -0.06
    å½
    -0.06
    ansa
    -0.06
    âĶ¬
    -0.06
     entirety
    -0.06
     ëĺIJíķľ
    -0.06
     explicitly
    -0.06
    POSITIVE LOGITS
    -Sah
    0.09
     erotische
    0.07
     erotisch
    0.07
    .SEVER
    0.07
    æŁĦ
    0.07
     cigaret
    0.07
    olet
    0.07
     surtout
    0.07
    /Foundation
    0.07
    kiye
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.