© 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. 93123
    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
    ieren
    -0.06
    GAN
    -0.06
    ù
    -0.06
    ONGL
    -0.06
    â
    -0.06
    mal
    -0.06
    elan
    -0.06
     cliffs
    -0.06
    arch
    -0.05
    اÙĤØ©
    -0.05
    POSITIVE LOGITS
    ayout
    0.07
     поба
    0.07
    oves
    0.07
     McCart
    0.07
    ,www
    0.07
    åĨĮ
    0.07
     rowspan
    0.07
    -ves
    0.06
    icates
    0.06
    Æ°á»Ł
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.