© 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 EvalsExportsinterp-engineNEWAPI 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. 86442
    Prev
    Next
    INDEX
    Explanations

    references to Scandinavian culture and history

    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
     eldre
    -0.07
    phis
    -0.06
     voksne
    -0.06
     Gecko
    -0.06
    ascar
    -0.06
    ucker
    -0.06
     Vz
    -0.06
     Cuban
    -0.06
    ear
    -0.06
    ques
    -0.05
    POSITIVE LOGITS
     Sweden
    0.15
     Swedish
    0.14
     Scandinavian
    0.14
     Oslo
    0.14
     Scandin
    0.14
     Norway
    0.14
     Norwegian
    0.13
    gaard
    0.13
     Stockholm
    0.12
     Lars
    0.12
    Activations Density 0.187%

    No Known Activations