© 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. 86456
    Prev
    Next
    INDEX
    Explanations

    references to cleaning products and their effectiveness

    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
    rette
    -0.07
     construct
    -0.06
    trap
    -0.06
     Weaver
    -0.06
    stdout
    -0.06
    /platform
    -0.05
    Suffix
    -0.05
    assi
    -0.05
    ouver
    -0.05
    .construct
    -0.05
    POSITIVE LOGITS
     cleaning
    0.10
     Cleaning
    0.10
     Stub
    0.08
     cleaners
    0.08
     Household
    0.08
     household
    0.08
    Cleaning
    0.07
     deter
    0.07
     Cleaner
    0.07
     cleaner
    0.07
    Activations Density 0.035%

    No Known Activations