© 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. 17-LLAMASCOPE-RES-131K
    11. 130364
    Prev
    Next
    INDEX
    Explanations

    locations and landmarks in Québec and surrounding areas

    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
     Australian
    -0.08
    Australian
    -0.07
     Australians
    -0.07
     Australia
    -0.07
     Lin
    -0.07
    NZ
    -0.06
     NZ
    -0.06
    ulus
    -0.06
    ipse
    -0.06
    ¼
    -0.06
    POSITIVE LOGITS
     Montreal
    0.11
     Québec
    0.09
     Quebec
    0.09
     Qué
    0.09
     McGill
    0.08
     Canadiens
    0.08
    erve
    0.07
    ike
    0.07
     Assassin
    0.07
    tréal
    0.07
    Activations Density 0.061%

    No Known Activations