© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 26344
    Prev
    Next
    INDEX
    Explanations

    references to zoning and construction approvals

    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
    reak
    -0.08
    agues
    -0.07
     dim
    -0.07
    io
    -0.07
    innie
    -0.07
    ago
    -0.06
    ï¸
    -0.06
    ::<
    -0.06
    IO
    -0.06
    ergus
    -0.06
    POSITIVE LOGITS
    etting
    0.07
     Mixed
    0.07
    551
    0.07
     areas
    0.07
    ledo
    0.07
    Mixed
    0.07
     mixed
    0.06
    alth
    0.06
    elib
    0.06
    amento
    0.06
    Activations Density 0.007%

    No Known Activations