© 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. 9-LLAMASCOPE-RES-131K
    11. 96923
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial and tax-related concepts

    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
    té
    -0.07
    tuk
    -0.07
    LocalizedString
    -0.07
    اساس
    -0.07
    avig
    -0.06
    íĥķ
    -0.06
    TabControl
    -0.06
    мом
    -0.06
     ãģ¿
    -0.06
    ColumnName
    -0.06
    POSITIVE LOGITS
     factorial
    0.07
    ureen
    0.07
     env
    0.06
     Hood
    0.06
     triangle
    0.06
    ufen
    0.06
     Maiden
    0.06
    åij¼
    0.06
     tail
    0.06
     hood
    0.06
    Activations Density 0.005%

    No Known Activations