© 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. 29417
    Prev
    Next
    INDEX
    Explanations

    mentions of locations and affiliations within the United States

    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
     Florida
    -0.10
     Tampa
    -0.10
     Atlanta
    -0.10
     Georgia
    -0.09
     Jacksonville
    -0.09
     Perth
    -0.09
    Florida
    -0.09
    Atlanta
    -0.08
    Georgia
    -0.08
     Seattle
    -0.07
    POSITIVE LOGITS
     Nebraska
    0.20
     Omaha
    0.19
    braska
    0.13
     Sioux
    0.11
     Kansas
    0.11
    Kansas
    0.11
     Iowa
    0.11
     Prairie
    0.10
     Lincoln
    0.10
     Midwest
    0.09
    Activations Density 0.060%

    No Known Activations