© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16904
    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
    \admin
    -0.08
    rase
    -0.07
    innacle
    -0.07
    olumn
    -0.07
    нож
    -0.06
    ÑĢив
    -0.06
    ymb
    -0.06
    estatus
    -0.06
    UTO
    -0.06
    ãĥ³ãĤº
    -0.06
    POSITIVE LOGITS
     marketing
    0.06
     Hemisphere
    0.06
     third
    0.06
     social
    0.06
     postponed
    0.06
     sociale
    0.06
    追
    0.06
     íĴį
    0.06
     profit
    0.06
    mma
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.