© 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. 15239
    Prev
    Next
    INDEX
    Explanations

    themes related to racism and prejudice

    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
    iez
    -0.09
    ipay
    -0.09
    ystore
    -0.09
    ÑĢог
    -0.08
    arResult
    -0.08
    ÑĢеменно
    -0.08
    pedo
    -0.08
    mps
    -0.08
    alars
    -0.08
    ibbon
    -0.08
    POSITIVE LOGITS
     racism
    0.10
     race
    0.10
     Race
    0.09
     racial
    0.08
    Race
    0.08
     whites
    0.08
     discrimination
    0.08
    0.07
     rac
    0.07
     races
    0.07
    Activations Density 0.030%

    No Known Activations