© 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. 30920
    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
    iris
    -0.08
    uru
    -0.07
    mac
    -0.06
    .scalablytyped
    -0.06
    ledger
    -0.06
    rog
    -0.06
    quare
    -0.06
    erp
    -0.06
    nost
    -0.06
    izo
    -0.06
    POSITIVE LOGITS
     gastr
    0.06
    ìĸ¼
    0.06
     pile
    0.06
    belt
    0.06
    neutral
    0.06
    æŦ
    0.06
    actus
    0.06
     Calif
    0.05
     editor
    0.05
    atte
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.