© 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. 130604
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and business agreements

    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
    apia
    -0.07
    ìĹ´
    -0.06
    iek
    -0.06
    ekl
    -0.06
    POS
    -0.06
     extrad
    -0.06
    èģ
    -0.06
    atorium
    -0.06
    imest
    -0.06
    ết
    -0.06
    POSITIVE LOGITS
     Defense
    0.09
     Military
    0.08
     Defence
    0.08
     military
    0.08
     Government
    0.08
     Federal
    0.08
     federal
    0.08
     defence
    0.08
     defense
    0.07
     missions
    0.07
    Activations Density 0.038%

    No Known Activations