© 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 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. 96761
    Prev
    Next
    INDEX
    Explanations

    concepts related to international or global contexts

    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
    ogy
    -0.06
     pii
    -0.06
    osaur
    -0.06
    deen
    -0.06
     Cong
    -0.06
    zin
    -0.06
     Myers
    -0.06
    ilton
    -0.06
     Ferdinand
    -0.05
    ÙĤØ·
    -0.05
    POSITIVE LOGITS
     foreign
    0.10
     overseas
    0.09
    foreign
    0.08
     abroad
    0.07
     foreigners
    0.07
     stran
    0.07
     Forums
    0.07
     Foreign
    0.07
     dál
    0.07
    ãĤ¦ãĤ¹
    0.07
    Activations Density 0.186%

    No Known Activations