© 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 EvalsExportsinterp-engineNEWAPI 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. 5061
    Prev
    Next
    INDEX
    Explanations

    references to washing dishes and associated tasks or items

    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
    ican
    -0.07
     canv
    -0.07
    BuilderInterface
    -0.07
    ÙĪزÛĮ
    -0.06
     ç«
    -0.06
    inha
    -0.06
    HeaderValue
    -0.06
    rica
    -0.06
    mour
    -0.06
    assis
    -0.06
    POSITIVE LOGITS
     dishwasher
    0.09
     cleaning
    0.09
     deter
    0.07
     Cleaning
    0.07
     detergent
    0.07
    ully
    0.07
     dish
    0.07
    itted
    0.07
     cleaners
    0.06
    bsub
    0.06
    Activations Density 0.013%

    No Known Activations