© 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. 62424
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, particularly in the context of higher education and communities

    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
    ele
    -0.08
    rof
    -0.07
    -regexp
    -0.07
    ulu
    -0.07
    seg
    -0.07
    ãĥ¼ãĤº
    -0.07
    irket
    -0.07
    589
    -0.07
    #
    -0.07
    yses
    -0.07
    POSITIVE LOGITS
     Island
    0.07
    allest
    0.06
     latter
    0.06
     Loop
    0.06
    bury
    0.06
    itian
    0.06
     Leone
    0.06
    angelo
    0.06
    ington
    0.06
     Crosby
    0.06
    Activations Density 0.001%

    No Known Activations