© 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. 95270
    Prev
    Next
    INDEX
    Explanations

    references to geopolitical contexts and territorial issues

    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
    apo
    -0.07
    ji
    -0.06
    ths
    -0.06
    оба
    -0.06
     пÑĢид
    -0.06
    Normal
    -0.06
    еÑģа
    -0.06
    rn
    -0.06
     Mek
    -0.06
    oun
    -0.05
    POSITIVE LOGITS
    erot
    0.07
    modulo
    0.07
    Memcpy
    0.06
     nay
    0.06
     Wel
    0.06
    Ł
    0.06
    otive
    0.06
    corr
    0.06
    _nsec
    0.06
    utherford
    0.06
    Activations Density 0.053%

    No Known Activations