© 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. 75935
    Prev
    Next
    INDEX
    Explanations

    references related to governmental fraud and associated legal terms

    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
    ÑĪин
    -0.06
    izio
    -0.06
     Offensive
    -0.06
     vir
    -0.06
    okud
    -0.06
    SEG
    -0.06
    à¥įरह
    -0.06
    åĮ
    -0.06
    _additional
    -0.06
     offensive
    -0.06
    POSITIVE LOGITS
    enci
    0.07
    erken
    0.07
     imminent
    0.07
     kred
    0.07
    bate
    0.06
    .getMap
    0.06
    hm
    0.06
     official
    0.06
    tester
    0.06
     Elm
    0.06
    Activations Density 0.030%

    No Known Activations