© 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. 72475
    Prev
    Next
    INDEX
    Explanations

    mentions of Indigenous peoples and their cultural practices

    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
    aeper
    -0.07
    OMPI
    -0.07
     nigeria
    -0.06
     localVar
    -0.06
    èn
    -0.06
    تÙĩا
    -0.06
     ØŃاÙģظ
    -0.06
    createForm
    -0.06
    -worker
    -0.06
    izmet
    -0.06
    POSITIVE LOGITS
     Indian
    0.09
     Native
    0.09
     Indians
    0.07
    Native
    0.07
    Apache
    0.07
     indian
    0.06
     Crazy
    0.06
     Apache
    0.06
    ëĭ¥
    0.06
    Indian
    0.06
    Activations Density 0.005%

    No Known Activations