© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 77494
    Prev
    Next
    INDEX
    Explanations

    terms related to menstrual health and abnormalities

    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
     Guaranteed
    -0.07
     opc
    -0.07
    oreach
    -0.07
     Rentals
    -0.07
    æ··
    -0.06
    opa
    -0.06
    Ãı
    -0.06
    rim
    -0.06
    lé
    -0.06
    luent
    -0.06
    POSITIVE LOGITS
     extreme
    0.08
     Extreme
    0.08
     beyond
    0.07
    Marshal
    0.07
    erchant
    0.07
    Anchor
    0.07
    yor
    0.07
    PCS
    0.06
     persisted
    0.06
    Extreme
    0.06
    Activations Density 0.012%

    No Known Activations