© 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. 125109
    Prev
    Next
    INDEX
    Explanations

    phrases related to support and resources for caregivers and individuals experiencing health challenges

    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
     ones
    -0.08
    ierz
    -0.07
    895
    -0.07
     jobject
    -0.07
    OutOfBounds
    -0.07
    045
    -0.07
    avit
    -0.07
     riêng
    -0.07
    adol
    -0.06
    ctype
    -0.06
    POSITIVE LOGITS
     guidance
    0.10
     advice
    0.09
     support
    0.09
     assistance
    0.08
     information
    0.08
     encouragement
    0.08
     insight
    0.07
     help
    0.07
     solutions
    0.07
     direction
    0.07
    Activations Density 0.026%

    No Known Activations