© 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. 16379
    Prev
    Next
    INDEX
    Explanations

    references to the New York Times

    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
    ute
    -0.07
     Cove
    -0.07
    elyn
    -0.06
    te
    -0.06
    ading
    -0.06
    holding
    -0.06
    trag
    -0.06
     Danh
    -0.05
    etic
    -0.05
    à¥įदर
    -0.05
    POSITIVE LOGITS
    TRACT
    0.07
    γκα
    0.07
    iddle
    0.07
     Deutschland
    0.07
    ãģ¹
    0.07
     dieta
    0.06
    iversit
    0.06
    ÌĨ
    0.06
    ì¡´
    0.06
    gua
    0.06
    Activations Density 0.004%

    No Known Activations