© 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. 9-LLAMASCOPE-RES-131K
    11. 96262
    Prev
    Next
    INDEX
    Explanations

    terms related to ethnic and cultural identity, particularly in the context of history

    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
    okes
    -0.07
    ourd
    -0.07
    gart
    -0.07
    keterangan
    -0.07
    inkle
    -0.07
    uze
    -0.07
    jee
    -0.07
    pent
    -0.07
    omanip
    -0.07
    arak
    -0.07
    POSITIVE LOGITS
     sharpen
    0.06
    wind
    0.06
    (nil
    0.06
     OCC
    0.06
     menace
    0.05
     Mobility
    0.05
     mod
    0.05
    _province
    0.05
     scram
    0.05
    (Mod
    0.05
    Activations Density 0.008%

    No Known Activations