© 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. 82273
    Prev
    Next
    INDEX
    Explanations

    elements related to emotional and behavioral conditions in children and adolescents

    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
    indow
    -0.08
    Ľå»º
    -0.08
    CKER
    -0.07
    ãĥ¼ãĥIJ
    -0.07
    assen
    -0.07
    stripe
    -0.07
    decltype
    -0.07
    дÑĢеÑģ
    -0.07
    ullets
    -0.07
    жи
    -0.07
    POSITIVE LOGITS
     suddenly
    0.09
     sudden
    0.08
     or
    0.07
     unusual
    0.07
     lately
    0.07
     unusually
    0.06
    auer
    0.06
     seem
    0.06
     odd
    0.06
    OrCreate
    0.06
    Activations Density 0.007%

    No Known Activations