© 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. 118728
    Prev
    Next
    INDEX
    Explanations

    references to government control and legal terminology

    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
    reur
    -0.06
    à¹ĥส
    -0.06
    ARENT
    -0.06
     Modular
    -0.06
    Mapped
    -0.06
     struk
    -0.06
    DU
    -0.06
    FP
    -0.06
     NOTICE
    -0.06
    _RCC
    -0.06
    POSITIVE LOGITS
     matters
    0.08
    merce
    0.07
    تع
    0.07
    gency
    0.06
     dil
    0.06
    Äįan
    0.06
    964
    0.06
    eteria
    0.06
     foreigners
    0.06
     Matters
    0.06
    Activations Density 0.009%

    No Known Activations