© 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. 2477
    Prev
    Next
    INDEX
    Explanations

    terms related to landmarks or notable locations

    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
    enk
    -0.08
    TINGS
    -0.08
    UDO
    -0.08
    udo
    -0.08
    ött
    -0.07
    quo
    -0.07
    tings
    -0.07
    overy
    -0.07
    /*č↵
    -0.07
    éłĤ
    -0.07
    POSITIVE LOGITS
    /Foundation
    0.08
    stay
    0.07
    cki
    0.07
    most
    0.07
    ski
    0.07
    ria
    0.07
    ately
    0.07
    so
    0.07
    edia
    0.07
    rect
    0.06
    Activations Density 0.003%

    No Known Activations