© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125009
    Prev
    Next
    INDEX
    Explanations

    geographic locations and regions related to North America, Asia, and Oceania

    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
    alo
    -0.07
    oui
    -0.07
    alaria
    -0.07
    .jd
    -0.07
     foreigners
    -0.07
    illard
    -0.07
    OMPI
    -0.07
     SavaÅŁ
    -0.06
     ä½ı
    -0.06
    ¡´
    -0.06
    POSITIVE LOGITS
    uyá»ĩt
    0.07
    .::
    0.06
    én
    0.06
    æĵ¦
    0.06
     Rab
    0.06
    ceipt
    0.05
    rink
    0.05
    Sink
    0.05
     Hurt
    0.05
    å®Ĺ
    0.05
    Activations Density 0.001%

    No Known Activations