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

    Neuronpedia

    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. 77921
    Prev
    Next
    INDEX
    Explanations

    terms related to racism and discrimination, including both direct references to racism and associated concepts

    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
    lify
    -0.08
    mente
    -0.07
    iterals
    -0.07
    onas
    -0.07
    achie
    -0.07
    änd
    -0.07
    ogue
    -0.06
    iros
    -0.06
    vale
    -0.06
    igar
    -0.06
    POSITIVE LOGITS
    uzzi
    0.07
    emic
    0.06
    باز
    0.06
    pit
    0.06
     rac
    0.06
    imbus
    0.06
     Rac
    0.06
    coon
    0.06
    ully
    0.06
     padd
    0.06
    Activations Density 0.007%

    No Known Activations