© 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 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. 87415
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to diversity and inclusion in various contexts

    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
    Ïĩα
    -0.07
    abay
    -0.07
    ilar
    -0.07
    rawl
    -0.07
     Venue
    -0.07
    calar
    -0.07
    igan
    -0.07
    reature
    -0.07
    arena
    -0.07
    nth
    -0.07
    POSITIVE LOGITS
    /div
    0.07
     diversity
    0.06
    related
    0.06
    -related
    0.06
     Diversity
    0.06
     æ©
    0.06
     Wheel
    0.06
     commission
    0.06
    Ľi
    0.05
     Todd
    0.05
    Activations Density 0.008%

    No Known Activations