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. 5677
    Prev
    Next
    INDEX
    Explanations

    terms related to equal opportunity and non-discrimination in employment

    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
    ÑĢд
    -0.07
    Ñĩе
    -0.06
    atre
    -0.06
    ignum
    -0.06
    indh
    -0.06
    ocks
    -0.06
    à¸Ńà¸Ķ
    -0.06
    odon
    -0.05
     spécial
    -0.05
     commod
    -0.05
    POSITIVE LOGITS
     employer
    0.12
     Employer
    0.10
    employer
    0.10
     employers
    0.09
     institution
    0.07
     provider
    0.07
    Employ
    0.07
     workplace
    0.07
    jeme
    0.07
     Institution
    0.06
    Activations Density 0.002%

    No Known Activations