© 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. 22-LLAMASCOPE-RES-131K
    11. 3593
    Prev
    Next
    INDEX
    Explanations

    phrases related to returns, refunds, and buyer responsibilities in 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
     Incontri
    -0.07
    arov
    -0.06
    asha
    -0.06
    ossier
    -0.06
    ais
    -0.06
    oola
    -0.06
    illis
    -0.06
    ulse
    -0.06
    ouden
    -0.06
    earn
    -0.06
    POSITIVE LOGITS
     Hamp
    0.06
     LENG
    0.06
    ERCHANT
    0.06
    omi
    0.06
     baj
    0.06
     drowned
    0.06
     newName
    0.06
     Classes
    0.06
    efault
    0.06
     leggings
    0.06
    Activations Density 0.003%

    No Known Activations