© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87954
    Prev
    Next
    INDEX
    Explanations

    significant geographical connections between cities and political discourse

    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
     Memphis
    -0.07
     Mississippi
    -0.07
     Ramsey
    -0.07
     Trinidad
    -0.07
     Missouri
    -0.07
     Zion
    -0.07
     Singapore
    -0.07
     Ghana
    -0.06
     singapore
    -0.06
     Puerto
    -0.06
    POSITIVE LOGITS
     Afghan
    0.13
     Afghanistan
    0.13
     Kabul
    0.11
     Taliban
    0.10
    #af
    0.09
     Provincial
    0.08
    ardash
    0.08
    oki
    0.08
     provincial
    0.07
     province
    0.07
    Activations Density 0.076%

    No Known Activations