© 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. 22-LLAMASCOPE-RES-131K
    11. 4044
    Prev
    Next
    INDEX
    Explanations

    key concepts related to political and economic theories, particularly socialism and communism

    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
    uncio
    -0.07
    sted
    -0.07
    HH
    -0.06
    714
    -0.06
     neoliberal
    -0.06
     chá»ĭu
    -0.06
     overst
    -0.06
    elden
    -0.06
     discreet
    -0.06
     extrav
    -0.06
    POSITIVE LOGITS
     ownership
    0.09
     Ownership
    0.09
     production
    0.08
     cooper
    0.08
     workers
    0.08
     Production
    0.08
     cooperative
    0.08
    ownership
    0.07
    -production
    0.07
     Cooperative
    0.07
    Activations Density 0.028%

    No Known Activations