© 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 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. 78491
    Prev
    Next
    INDEX
    Explanations

    terms related to dental and health services

    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
     Uran
    -0.06
     "
    -0.06
     mare
    -0.06
     “
    -0.05
    11
    -0.05
    ä¹ħ
    -0.05
    lah
    -0.05
    ,
    -0.05
     Practical
    -0.05
    209
    -0.05
    POSITIVE LOGITS
    formace
    0.09
    uze
    0.08
    regor
    0.08
    ucci
    0.08
    DITION
    0.08
    .bunifuFlatButton
    0.08
    ceries
    0.07
    plementation
    0.07
    heiten
    0.07
    kün
    0.07
    Activations Density 0.025%

    No Known Activations