© 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. 92103
    Prev
    Next
    INDEX
    Explanations

    references to Indigenous cultural aspects and identities

    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
    avia
    -0.06
     Nielsen
    -0.06
    룡
    -0.06
    arth
    -0.06
    oldt
    -0.06
    gger
    -0.06
    qing
    -0.06
    ÃľM
    -0.06
    ulet
    -0.06
    rex
    -0.06
    POSITIVE LOGITS
     Indian
    0.08
    assin
    0.07
    álo
    0.07
    apache
    0.07
     Moh
    0.07
     Apache
    0.07
    Indian
    0.07
     Dakota
    0.07
    erokee
    0.07
    quam
    0.07
    Activations Density 0.035%

    No Known Activations