© 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. 89005
    Prev
    Next
    INDEX
    Explanations

    references to local government and community organization

    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
     worldwide
    -0.08
    istrovstvÃŃ
    -0.07
    .eth
    -0.07
     Worldwide
    -0.07
    é¾Ħ
    -0.07
    alama
    -0.07
     SvÄĽt
    -0.07
    åħ¨çIJĥ
    -0.07
    hlen
    -0.07
    bstract
    -0.07
    POSITIVE LOGITS
     Regional
    0.08
     regional
    0.07
    915
    0.07
    495
    0.07
    Regional
    0.07
    ัà¸ĩà¸ģ
    0.07
    lesh
    0.06
     towns
    0.06
    shared
    0.06
     county
    0.06
    Activations Density 0.004%

    No Known Activations