© 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. 9-LLAMASCOPE-RES-131K
    11. 97234
    Prev
    Next
    INDEX
    Explanations

    words that indicate moral urgency or demand for accountability

    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
     Pic
    -0.06
     Deutsch
    -0.06
     Mand
    -0.06
    alth
    -0.06
     bip
    -0.06
     Deprecated
    -0.06
     Kitt
    -0.06
     Cousins
    -0.05
     Birds
    -0.05
     forg
    -0.05
    POSITIVE LOGITS
    /antlr
    0.08
     Aires
    0.08
    baugh
    0.08
    ConverterFactory
    0.07
    ãģ¡ãģ¯
    0.07
    uela
    0.07
     CEL
    0.07
    aed
    0.07
    .generated
    0.07
    .jquery
    0.07
    Activations Density 0.000%

    No Known Activations