© 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. 59800
    Prev
    Next
    INDEX
    Explanations

    concepts related to self-determination and independence of nations

    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
    .pair
    -0.07
    istar
    -0.07
    azer
    -0.07
    uzey
    -0.07
     tay
    -0.07
    jom
    -0.07
    istra
    -0.07
    ipar
    -0.07
    onces
    -0.07
    abra
    -0.07
    POSITIVE LOGITS
     continuation
    0.07
    install
    0.07
    575
    0.06
     recent
    0.06
     previously
    0.06
     recently
    0.06
     neutr
    0.05
     Insight
    0.05
     modes
    0.05
     Recently
    0.05
    Activations Density 0.054%

    No Known Activations