© 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. 55373
    Prev
    Next
    INDEX
    Explanations

    phrases related to banking and lending practices

    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
     vmax
    -0.07
    egov
    -0.07
    rial
    -0.06
    AllowAnonymous
    -0.06
    ripe
    -0.06
     rever
    -0.06
    Shared
    -0.06
    лика
    -0.06
    plaintext
    -0.06
     Glover
    -0.06
    POSITIVE LOGITS
     supply
    0.08
     credit
    0.07
     Supply
    0.07
    supply
    0.06
    upply
    0.06
    TEGER
    0.06
     lending
    0.06
    âĢĮرس
    0.06
     supplies
    0.06
     available
    0.06
    Activations Density 0.012%

    No Known Activations