© 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. 129864
    Prev
    Next
    INDEX
    Explanations

    concepts related to choice and personal agency in education

    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
    /mainwindow
    -0.08
     seins
    -0.07
    LOUR
    -0.07
    ãĤ¤ãĤº
    -0.07
    _dma
    -0.07
    kees
    -0.07
    еди
    -0.07
    ckill
    -0.07
    .cf
    -0.07
    opper
    -0.07
    POSITIVE LOGITS
     flex
    0.09
     flexibility
    0.08
     freely
    0.08
     flexible
    0.08
     Flex
    0.08
    flex
    0.07
     potentially
    0.07
    Flex
    0.07
     dev
    0.07
     experiment
    0.07
    Activations Density 0.020%

    No Known Activations