© 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. 84944
    Prev
    Next
    INDEX
    Explanations

    phrases related to regional economic agreements and cooperation

    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
    ormsg
    -0.07
     Bere
    -0.07
     Nigerian
    -0.07
    arg
    -0.06
     Sudan
    -0.06
    #
    -0.06
    ordum
    -0.06
     Niger
    -0.06
     Polar
    -0.06
    abra
    -0.06
    POSITIVE LOGITS
     Asia
    0.15
     Asian
    0.13
    Asian
    0.13
    Asia
    0.12
     asia
    0.11
     Asians
    0.11
     asian
    0.10
     Singapore
    0.09
     Pacific
    0.09
     asiat
    0.09
    Activations Density 0.274%

    No Known Activations