© 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 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. 77201
    Prev
    Next
    INDEX
    Explanations

    themes related to educational and social inequities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    pawn
    -0.07
    eya
    -0.06
    oga
    -0.06
    errated
    -0.06
    à¹īà¸Ńม
    -0.06
    essel
    -0.06
    idar
    -0.06
    vil
    -0.06
    ulk
    -0.06
    plen
    -0.06
    POSITIVE LOGITS
     gap
    0.08
    Gap
    0.07
     between
    0.07
     stubborn
    0.07
    gap
    0.07
     difference
    0.07
     Magn
    0.07
    between
    0.07
     persist
    0.06
     Gap
    0.06
    Activations Density 0.010%

    No Known Activations