© 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. 72570
    Prev
    Next
    INDEX
    Explanations

    terms related to diversity and inclusion, particularly in the context of race, gender, and sexual orientation

    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
    ĨĴ
    -0.07
    akra
    -0.07
    uxtap
    -0.07
    anax
    -0.07
    andest
    -0.07
    ilor
    -0.07
    ToLeft
    -0.07
    .gdx
    -0.07
    izon
    -0.07
    exus
    -0.07
    POSITIVE LOGITS
    nock
    0.06
    èĨ
    0.06
    ERRU
    0.06
    inos
    0.06
    ha
    0.06
    üt
    0.06
     parody
    0.05
    ems
    0.05
    096
    0.05
    GA
    0.05
    Activations Density 0.002%

    No Known Activations