© 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. 17-LLAMASCOPE-RES-131K
    11. 55438
    Prev
    Next
    INDEX
    Explanations

    references to the geographical location "Suffolk."

    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
    ẻ
    -0.08
     Tay
    -0.07
    à¸
    -0.07
    ecut
    -0.07
    .CopyTo
    -0.07
    æı
    -0.07
    loff
    -0.07
    زا
    -0.07
    ÙħÛĮÙĨ
    -0.07
    ॰
    -0.07
    POSITIVE LOGITS
     Rol
    0.06
    constant
    0.06
     Pell
    0.06
    anst
    0.05
    woord
    0.05
    vice
    0.05
    angs
    0.05
     complex
    0.05
    xyz
    0.05
     vast
    0.05
    Activations Density 0.000%

    No Known Activations