© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76012
    Prev
    Next
    INDEX
    Explanations

    references to government officials and their roles

    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
    anean
    -0.06
    arin
    -0.06
     neighbourhood
    -0.06
    ase
    -0.06
    ŀ
    -0.06
    Ŀ
    -0.06
    sten
    -0.05
     parish
    -0.05
     congreg
    -0.05
     guild
    -0.05
    POSITIVE LOGITS
     Governor
    0.12
     governor
    0.12
     Governors
    0.12
     governors
    0.11
    Govern
    0.10
     гÑĥбеÑĢ
    0.09
     gubern
    0.07
    erie
    0.06
    å·ŀ
    0.06
    à¹ģà¸Ĺà¸Ļ
    0.06
    Activations Density 0.064%

    No Known Activations