© 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. 56944
    Prev
    Next
    INDEX
    Explanations

    proper nouns and official titles related to government and tourism organizations

    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
     district
    -0.08
     city
    -0.08
    city
    -0.07
     Local
    -0.07
     local
    -0.07
    .scalablytyped
    -0.07
     county
    -0.07
    Local
    -0.06
     locally
    -0.06
     District
    -0.06
    POSITIVE LOGITS
    ż
    0.07
    Secretary
    0.07
    à¹Ģà¸Ńà¸ĩ
    0.07
    eterminate
    0.07
    òng
    0.07
    ê°ĢìļĶ
    0.07
    iž
    0.07
     sink
    0.06
    Æ°á»Ľng
    0.06
    ož
    0.06
    Activations Density 0.057%

    No Known Activations