© 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. 69412
    Prev
    Next
    INDEX
    Explanations

    geographical locations and related entities

    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
     Oregon
    -0.10
    Oregon
    -0.09
    Seattle
    -0.08
     Portland
    -0.07
    ÅĽ
    -0.07
     Seattle
    -0.07
    osci
    -0.07
    Portland
    -0.07
    ascade
    -0.07
     Tacoma
    -0.07
    POSITIVE LOGITS
     Bermuda
    0.15
     Bahamas
    0.13
     Berm
    0.11
     Caribbean
    0.11
     island
    0.09
     Cay
    0.08
     Belize
    0.08
     Newfoundland
    0.07
     Trinidad
    0.07
     Jamaica
    0.07
    Activations Density 0.006%

    No Known Activations