© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 60680
    Prev
    Next
    INDEX
    Explanations

    references to family caregivers and their roles

    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
    icon
    -0.07
    ertas
    -0.06
    /stdc
    -0.06
    EDI
    -0.06
     Jen
    -0.06
    INST
    -0.06
    μιÏĥ
    -0.06
    edes
    -0.06
    ÑĨеп
    -0.06
    anco
    -0.06
    POSITIVE LOGITS
     careg
    0.14
     caregiver
    0.11
     caring
    0.10
     caregivers
    0.10
     Alzheimer
    0.10
     care
    0.09
     Care
    0.09
    oger
    0.09
     cared
    0.09
     caret
    0.08
    Activations Density 0.155%

    No Known Activations