© 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 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. 87464
    Prev
    Next
    INDEX
    Explanations

    specific product attributes and terms related to cleaning products

    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
    icl
    -0.06
    weise
    -0.06
    ÑĢиÑĩ
    -0.06
     Beacon
    -0.06
    vanished
    -0.06
    .VisualBasic
    -0.06
    окон
    -0.06
    dehy
    -0.06
    INAL
    -0.06
    ãĤ¹ãĥĿ
    -0.06
    POSITIVE LOGITS
    ův
    0.07
    ARCHAR
    0.06
    owski
    0.06
    imos
    0.06
    icrous
    0.06
    istrovstvÃŃ
    0.06
    .org
    0.06
     ли
    0.06
    ráf
    0.06
    aucoup
    0.06
    Activations Density 0.018%

    No Known Activations