© 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. 88629
    Prev
    Next
    INDEX
    Explanations

    terms related to Alzheimer's disease and its effects

    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
    Desktop
    -0.07
     pulmonary
    -0.07
    cela
    -0.06
    éijij
    -0.06
    IRTH
    -0.06
     Bow
    -0.06
     Desktop
    -0.06
    ãĥijãĥ³
    -0.06
     statically
    -0.06
    мп
    -0.06
    POSITIVE LOGITS
     Alzheimer
    0.18
     dementia
    0.16
    ementia
    0.13
    zheimer
    0.13
     amy
    0.12
     Memory
    0.12
     memory
    0.12
    memory
    0.11
    Memory
    0.11
     MEMORY
    0.10
    Activations Density 0.062%

    No Known Activations