© 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. 76476
    Prev
    Next
    INDEX
    Explanations

    references to New York City and its characteristics

    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
    omer
    -0.09
    uild
    -0.07
    ink
    -0.06
    ri
    -0.06
    ore
    -0.06
    co
    -0.06
    jo
    -0.06
    em
    -0.06
     Mal
    -0.06
    mins
    -0.06
    POSITIVE LOGITS
     city
    0.10
    city
    0.09
    -city
    0.08
     iconic
    0.08
    ãĥ¼ãĥĦ
    0.08
     CITY
    0.08
     cidade
    0.08
    emez
    0.08
     City
    0.08
     CultureInfo
    0.08
    Activations Density 0.024%

    No Known Activations