© 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. 58774
    Prev
    Next
    INDEX
    Explanations

    financial discussions related to taxation and economic inequalities

    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
    etter
    -0.06
    lector
    -0.06
    á»ĥn
    -0.06
    retty
    -0.06
    ustainable
    -0.06
     Lamar
    -0.06
    antino
    -0.06
    recated
    -0.06
    borrow
    -0.06
    _NT
    -0.06
    POSITIVE LOGITS
     wealthy
    0.09
     corporations
    0.09
     Wealth
    0.09
     profits
    0.09
     profit
    0.08
     wealthiest
    0.08
    profits
    0.08
     Wall
    0.08
     wealth
    0.08
     PROFITS
    0.08
    Activations Density 0.143%

    No Known Activations