© 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 EvalsExportsinterp-engineNEWAPI 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. 39547
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to locations, especially in the context of electricity or community services

    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
    æ¡Ĥ
    -0.08
    optera
    -0.07
    zÃŃ
    -0.07
    unsch
    -0.06
    nev
    -0.06
    atee
    -0.06
    imbus
    -0.06
    еÑĢаÑĤоÑĢ
    -0.06
    à¹Ģà¸ģà¸Ńร
    -0.06
    pter
    -0.06
    POSITIVE LOGITS
    ifax
    0.07
    _BIT
    0.06
    itesse
    0.06
    моÑģ
    0.06
    овиÑĩ
    0.06
    OOK
    0.06
    /vendors
    0.06
    itted
    0.06
     Sheet
    0.06
    lıyor
    0.06
    Activations Density 0.001%

    No Known Activations