© 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. 74328
    Prev
    Next
    INDEX
    Explanations

    terms related to white identity and supremacy

    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
    eson
    -0.10
    kün
    -0.09
    ngr
    -0.08
    огод
    -0.08
    icari
    -0.07
     ê°ķëĤ¨
    -0.07
     __("
    -0.07
    ixin
    -0.07
    cribe
    -0.07
    ä»ĺ
    -0.07
    POSITIVE LOGITS
    -white
    0.09
     White
    0.07
    -owned
    0.07
     white
    0.07
    -collar
    0.06
     supremacist
    0.06
    /english
    0.06
     Gins
    0.06
    -dominated
    0.06
     male
    0.06
    Activations Density 0.010%

    No Known Activations