Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5465
    Prev
    Next
    INDEX
    Explanations

    keywords related to labor issues and union activities

    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
    iyel
    -0.07
    azers
    -0.07
    ÙħاÙĨÛĮ
    -0.07
    ÑĤеÑĢи
    -0.07
    óÅĤ
    -0.06
     Dame
    -0.06
     Trap
    -0.06
     nors
    -0.06
    ificador
    -0.06
    çľī
    -0.06
    POSITIVE LOGITS
     GM
    0.11
     Detroit
    0.10
     plants
    0.10
    Detroit
    0.10
     Michigan
    0.09
     union
    0.09
     autom
    0.09
     Plants
    0.09
    GM
    0.09
     auto
    0.08
    Activations Density 0.024%

    No Known Activations