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

    Neuronpedia

    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. 86933
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and money

    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
    ieten
    -0.09
    ÑĪÑĥ
    -0.07
    รส
    -0.07
    asley
    -0.07
    ((__
    -0.07
    éĢģæĸĻçĦ¡æĸĻ
    -0.07
    oria
    -0.07
    zych
    -0.07
     hood
    -0.06
    ModelError
    -0.06
    POSITIVE LOGITS
     pocket
    0.08
    Pocket
    0.07
     pockets
    0.07
     ÙĨÙĤد
    0.07
    -pocket
    0.07
     Pocket
    0.06
    .biz
    0.06
     money
    0.06
     arbitrary
    0.06
    uros
    0.06
    Activations Density 0.028%

    No Known Activations