© 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. 15-LLAMASCOPE-RES-131K
    11. 26367
    Prev
    Next
    INDEX
    Explanations

    mentions of employment and self-employment classifications

    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
    ega
    -0.08
    AZY
    -0.08
    owski
    -0.08
    ernote
    -0.08
    anager
    -0.07
    ertas
    -0.07
    ë²Į
    -0.07
    _marshall
    -0.07
    erten
    -0.07
    INCT
    -0.07
    POSITIVE LOGITS
     stu
    0.06
     independent
    0.06
    LEX
    0.06
     sou
    0.06
     sour
    0.06
    lex
    0.06
     Dynam
    0.05
     forming
    0.05
    unch
    0.05
    éļ
    0.05
    Activations Density 0.006%

    No Known Activations