© 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. 17-LLAMASCOPE-RES-131K
    11. 59812
    Prev
    Next
    INDEX
    Explanations

    concepts related to intercultural communication and challenges

    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
    Accessibility
    -0.08
    anus
    -0.07
    arel
    -0.07
    串
    -0.07
    amp
    -0.06
    angan
    -0.06
    odyn
    -0.06
    alse
    -0.06
    atu
    -0.06
    Backing
    -0.06
    POSITIVE LOGITS
     Receiver
    0.07
     receivers
    0.07
     Western
    0.07
    ô
    0.06
    <context
    0.06
     differences
    0.06
     cross
    0.06
     è£
    0.06
     western
    0.06
    .Cross
    0.06
    Activations Density 0.015%

    No Known Activations