© 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. 9-LLAMASCOPE-RES-131K
    11. 94644
    Prev
    Next
    INDEX
    Explanations

    references to various ethnicities and racial groups

    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
    arias
    -0.08
    ighet
    -0.08
    arn
    -0.08
    ourg
    -0.07
    ูà¸Ļ
    -0.07
    neau
    -0.07
    rouw
    -0.07
     Downing
    -0.07
    enor
    -0.07
    inand
    -0.07
    POSITIVE LOGITS
    imler
    0.06
     disag
    0.06
     blend
    0.06
     bore
    0.06
     Güven
    0.06
     lore
    0.06
    à§į
    0.05
    -U
    0.05
    ibri
    0.05
     whom
    0.05
    Activations Density 0.024%

    No Known Activations