© 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. 62813
    Prev
    Next
    INDEX
    Explanations

    references to Indigenous peoples and their experiences with colonialism

    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
    rame
    -0.08
    bud
    -0.07
     semiclass
    -0.07
    æģ¯
    -0.07
    _ISR
    -0.07
    bru
    -0.07
     NavParams
    -0.07
    hei
    -0.06
    umes
    -0.06
    abei
    -0.06
    POSITIVE LOGITS
     contact
    0.07
     Indigenous
    0.07
     Contact
    0.06
     contacts
    0.06
     Contacts
    0.06
    contact
    0.06
     Native
    0.06
    -contact
    0.06
     native
    0.06
    /contact
    0.05
    Activations Density 0.010%

    No Known Activations