© 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. 95458
    Prev
    Next
    INDEX
    Explanations

    concepts related to class struggle and socioeconomic systems

    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
     conservatism
    -0.07
    é§IJ
    -0.07
    reme
    -0.06
    ocode
    -0.06
     Stretch
    -0.06
    dra
    -0.06
    eut
    -0.06
     turist
    -0.06
    bÃŃ
    -0.06
    omedical
    -0.06
    POSITIVE LOGITS
     Worker
    0.10
     worker
    0.09
     workers
    0.09
     Marx
    0.09
     Workers
    0.09
    worker
    0.08
    workers
    0.08
    Worker
    0.08
    -worker
    0.08
     labour
    0.08
    Activations Density 0.040%

    No Known Activations