© 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. 30503
    Prev
    Next
    INDEX
    Explanations

    terms related to socioeconomic classes and labor dynamics

    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
    ipur
    -0.07
    etine
    -0.06
    icari
    -0.06
    uess
    -0.06
     libs
    -0.06
     erotico
    -0.06
    ÑĢей
    -0.06
    uss
    -0.06
    perator
    -0.06
    sandbox
    -0.06
    POSITIVE LOGITS
     Industrial
    0.10
     industrial
    0.10
    Industrial
    0.09
     labour
    0.08
     labor
    0.08
    ByText
    0.08
    ongsTo
    0.08
     factory
    0.07
     factories
    0.07
     Factory
    0.07
    Activations Density 0.021%

    No Known Activations