© 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. 120905
    Prev
    Next
    INDEX
    Explanations

    mentions of Alzheimer's and related neurodegenerative diseases

    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
    ̧
    -0.08
    -0.08
    ernes
    -0.07
    imits
    -0.07
    elsen
    -0.07
    itarian
    -0.07
    ä¼į
    -0.07
    zens
    -0.07
    .getAs
    -0.07
    ighbors
    -0.07
    POSITIVE LOGITS
     disease
    0.11
     Disease
    0.08
    -related
    0.07
     related
    0.07
    ellido
    0.07
    IBC
    0.06
     Zot
    0.06
     targetType
    0.06
     dementia
    0.06
     Toolbox
    0.06
    Activations Density 0.003%

    No Known Activations