© 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. 9-LLAMASCOPE-RES-131K
    11. 94935
    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
     gang
    -0.06
    urch
    -0.06
    ennie
    -0.06
    slt
    -0.06
     pun
    -0.06
     cl
    -0.05
     wit
    -0.05
    alles
    -0.05
     organized
    -0.05
    uren
    -0.05
    POSITIVE LOGITS
    ër
    0.08
    ButtonText
    0.07
    лин
    0.07
    Å¡ov
    0.07
    ziej
    0.07
    LAG
    0.07
     Oaks
    0.07
    جÙħ
    0.07
    ragments
    0.07
    setFlash
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.