Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5049
    Prev
    Next
    INDEX
    Explanations

    references to Alzheimer's disease

    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
    ÏĨÏħ
    -0.07
    ëĮ
    -0.07
    anka
    -0.06
    asant
    -0.06
    portun
    -0.06
     ju
    -0.06
    .CompareTo
    -0.06
    chan
    -0.06
    alu
    -0.06
    .ws
    -0.06
    POSITIVE LOGITS
    zheimer
    0.10
    's
    0.08
     forgetting
    0.08
    ’s
    0.08
    hip
    0.07
     disease
    0.07
     forget
    0.07
     ther
    0.07
     Alzheimer
    0.07
     amy
    0.07
    Activations Density 0.002%

    No Known Activations