© 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. 3546
    Prev
    Next
    INDEX
    Explanations

    references to city governance and municipal matters

    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
     Provincial
    -0.08
    çľģ
    -0.07
    uling
    -0.07
    ูล
    -0.07
    PEndPoint
    -0.07
    edik
    -0.07
    κÎŃ
    -0.07
    kili
    -0.07
    mpz
    -0.07
    .fit
    -0.06
    POSITIVE LOGITS
    wide
    0.10
    -wide
    0.08
    -owned
    0.08
     Attorney
    0.08
     Wide
    0.08
    emento
    0.07
    Wide
    0.07
     wide
    0.07
     Budget
    0.06
     attorney
    0.06
    Activations Density 0.015%

    No Known Activations