© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 128976
    Prev
    Next
    INDEX
    Explanations

    themes related to nationalism and ethnic conflicts

    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
    mé
    -0.07
    ané
    -0.07
    añ
    -0.07
     Zwe
    -0.07
    735
    -0.07
    aqu
    -0.06
     François
    -0.06
     Ukra
    -0.06
    holm
    -0.06
    æĢ
    -0.06
    POSITIVE LOGITS
     Serbian
    0.12
     Kosovo
    0.11
     Serbia
    0.11
     Ser
    0.09
    Drag
    0.09
     cevap
    0.09
     Drag
    0.09
     Yugosl
    0.08
    ije
    0.08
     Bosnia
    0.08
    Activations Density 0.086%

    No Known Activations