© 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. 119958
    Prev
    Next
    INDEX
    Explanations

    terms related to pregnancy and maternal health

    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
     childhood
    -0.08
    κοÏį
    -0.07
     Childhood
    -0.07
    æŃ¯
    -0.07
    juven
    -0.07
    roat
    -0.07
    ë²ķ
    -0.07
     adultos
    -0.07
    Vect
    -0.07
     Youth
    -0.07
    POSITIVE LOGITS
     gest
    0.14
     pregnant
    0.14
     pregnancy
    0.14
     trimest
    0.13
     Pregnancy
    0.13
     Pregn
    0.11
     Gest
    0.11
    preg
    0.11
     plac
    0.11
     gravid
    0.10
    Activations Density 0.097%

    No Known Activations