© 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. 55692
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and 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
    ourt
    -0.07
    contri
    -0.07
     Turnbull
    -0.07
    ÑĩеÑĢ
    -0.06
    ffic
    -0.06
    ijken
    -0.06
    /cat
    -0.06
    bour
    -0.06
    roke
    -0.06
    akin
    -0.06
    POSITIVE LOGITS
     transaction
    0.09
     transactions
    0.07
    transaction
    0.07
    .literal
    0.07
     matters
    0.07
     Transactions
    0.07
     deal
    0.06
     legality
    0.06
     deals
    0.06
     commercial
    0.06
    Activations Density 0.038%

    No Known Activations