© 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. 28622
    Prev
    Next
    INDEX
    Explanations

    references to laundry services or laundry-related activities

    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
    chio
    -0.09
    ogl
    -0.09
     èĩªåĬ¨çĶŁæĪIJ
    -0.08
    inality
    -0.07
    UNET
    -0.07
    czy
    -0.07
     addCriterion
    -0.07
    zoek
    -0.07
    nings
    -0.07
    fü
    -0.07
    POSITIVE LOGITS
    گاÙĩ
    0.07
     detergent
    0.07
    ares
    0.07
    thew
    0.06
    ette
    0.06
    न
    0.06
    tainment
    0.06
    -La
    0.06
    elin
    0.06
    erto
    0.06
    Activations Density 0.003%

    No Known Activations