© 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. 15-LLAMASCOPE-RES-131K
    11. 86944
    Prev
    Next
    INDEX
    Explanations

    concepts related to financial literacy and responsibility

    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
    mé
    -0.08
    hrad
    -0.07
    ificant
    -0.07
    azen
    -0.07
    оÑģлав
    -0.06
    quez
    -0.06
    اÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    -0.06
    Verts
    -0.06
    onic
    -0.06
    боÑĤ
    -0.06
    POSITIVE LOGITS
     sav
    0.07
     saving
    0.07
     Financial
    0.07
     money
    0.06
     financial
    0.06
     Money
    0.06
     MONEY
    0.06
     Sav
    0.06
     Hoover
    0.06
    ãĦ
    0.06
    Activations Density 0.014%

    No Known Activations