© 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 EvalsExportsinterp-engineNEWAPI 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. 105551
    Prev
    Next
    INDEX
    Explanations

    references to commissions and governmental inquiries, particularly in a financial or political context

    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
    edException
    -0.07
    uge
    -0.06
    iest
    -0.06
    ords
    -0.06
    uhl
    -0.06
    omu
    -0.06
    важ
    -0.06
    ponsible
    -0.06
    ameleon
    -0.06
    aston
    -0.06
    POSITIVE LOGITS
    "default
    0.07
    _firestore
    0.06
    оло
    0.06
    prav
    0.06
    anism
    0.06
     would
    0.06
     Marino
    0.06
    amo
    0.06
     Kab
    0.06
     scenarios
    0.06
    Activations Density 0.041%

    No Known Activations