© 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. 77701
    Prev
    Next
    INDEX
    Explanations

    phrases related to government and civic engagement

    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
     provinces
    -0.09
    åħ¨åĽ½
    -0.07
     CHARSET
    -0.07
    íĮĶ
    -0.07
    ODULE
    -0.07
    lsen
    -0.07
    ranges
    -0.07
    UNET
    -0.07
     Parliamentary
    -0.07
    çīĩ
    -0.07
    POSITIVE LOGITS
     municipal
    0.11
     city
    0.10
     ward
    0.09
     City
    0.08
     council
    0.08
     district
    0.08
     Municipal
    0.08
     municip
    0.08
     Ward
    0.08
     municipality
    0.08
    Activations Density 0.043%

    No Known Activations