© 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. 15-LLAMASCOPE-RES-131K
    11. 88558
    Prev
    Next
    INDEX
    Explanations

    references to different countries or geopolitical entities

    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
    ãĥ³ãĤº
    -0.09
    ãĥĮ
    -0.07
    uzzi
    -0.07
    entai
    -0.07
    uyen
    -0.07
    oppins
    -0.07
    iao
    -0.06
    ilo
    -0.06
    iza
    -0.06
    ARSER
    -0.06
    POSITIVE LOGITS
    ana
    0.07
    ieber
    0.07
    ida
    0.06
    gens
    0.06
    arat
    0.06
     alike
    0.06
    ipa
    0.06
    zzle
    0.06
    landa
    0.06
    218
    0.06
    Activations Density 0.011%

    No Known Activations