© 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. 126532
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations and associated experiences or activities

    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
     Spokane
    -0.10
     Seattle
    -0.09
     Alpine
    -0.09
     Yosemite
    -0.08
     yak
    -0.08
    /ubuntu
    -0.08
     Seahawks
    -0.08
     Tacoma
    -0.08
     Alps
    -0.07
     Yak
    -0.07
    POSITIVE LOGITS
     Memphis
    0.10
     Belize
    0.09
     Caribbean
    0.09
     Miami
    0.09
    Miami
    0.08
    ropical
    0.08
    Florida
    0.08
     sug
    0.08
     Gulf
    0.08
     Florida
    0.07
    Activations Density 0.002%

    No Known Activations