© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 108131
    Prev
    Next
    INDEX
    Explanations

    words and titles associated with business roles and professional positions

    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
    åľĴ
    -0.06
    _certificate
    -0.06
    eron
    -0.06
    ija
    -0.06
     crossorigin
    -0.06
    /commons
    -0.06
     BOT
    -0.06
    aren
    -0.06
    ulo
    -0.06
    елÑı
    -0.05
    POSITIVE LOGITS
     client
    0.10
     clients
    0.10
    Clients
    0.10
    -client
    0.10
    firm
    0.10
     firm
    0.10
     Clients
    0.09
     Client
    0.09
     Firm
    0.09
     CLIENT
    0.09
    Activations Density 0.134%

    No Known Activations