© 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. 74002
    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
    inh
    -0.07
    ><![
    -0.06
     shit
    -0.06
    kie
    -0.06
     '[
    -0.05
     nackte
    -0.05
    stvo
    -0.05
    rogate
    -0.05
     Below
    -0.05
     unsur
    -0.05
    POSITIVE LOGITS
    STEM
    0.07
    buz
    0.07
    жÑĥ
    0.07
    NetMessage
    0.07
    بÙĪاسطة
    0.07
    iversit
    0.07
     popis
    0.06
     STEM
    0.06
    malar
    0.06
    Äįer
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.