© 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. 129577
    Prev
    Next
    INDEX
    Explanations

    references to governmental departments and ministries

    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
    aku
    -0.08
    pte
    -0.07
    pais
    -0.07
    ExecutionContext
    -0.07
    .usage
    -0.06
    adla
    -0.06
    lected
    -0.06
     дÑĸ
    -0.06
    otherwise
    -0.06
    ·¸
    -0.06
    POSITIVE LOGITS
     Affairs
    0.09
     affairs
    0.08
    477
    0.07
    eller
    0.06
     Minister
    0.06
     Culture
    0.06
     portfolio
    0.06
    Culture
    0.06
     Cabinet
    0.06
     minister
    0.06
    Activations Density 0.042%

    No Known Activations