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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98294
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to fetal health and safety

    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
    addock
    -0.07
    Caption
    -0.07
    elig
    -0.07
    ymax
    -0.07
    ivy
    -0.07
    訳
    -0.06
    isen
    -0.06
    gh
    -0.06
    emek
    -0.06
    stå
    -0.06
    POSITIVE LOGITS
    594
    0.07
    hood
    0.07
    PIO
    0.06
    aminer
    0.06
     specialization
    0.06
    legg
    0.06
    713
    0.06
    /master
    0.06
    oker
    0.06
    _defaults
    0.05
    Activations Density 0.002%

    No Known Activations