© 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. 96657
    Prev
    Next
    INDEX
    Explanations

    monetary amounts or financial transactions

    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
     Died
    -0.06
    -digit
    -0.06
    anas
    -0.06
    å·§
    -0.06
     nic
    -0.06
    uil
    -0.06
    rav
    -0.06
    rus
    -0.06
    âĢŀV
    -0.06
     h
    -0.05
    POSITIVE LOGITS
    دÙĩ
    0.07
    oders
    0.07
    ahu
    0.07
    ableObject
    0.07
    zek
    0.07
    xae
    0.07
    ãģ¤ãģ¶
    0.07
    ãĤ¹ãĥŀ
    0.07
    RenderingContext
    0.06
    Ä©
    0.06
    Activations Density 0.002%

    No Known Activations