© 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. 124752
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement and funding issues

    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
    reten
    -0.08
    retty
    -0.07
    rlen
    -0.07
     दल
    -0.07
    rypt
    -0.07
     ikt
    -0.07
    rende
    -0.07
    æĴ®
    -0.07
    TextStyle
    -0.07
    icari
    -0.07
    POSITIVE LOGITS
     div
    0.07
     police
    0.07
     shifts
    0.06
     pods
    0.06
     Kelvin
    0.06
    .shift
    0.06
     Police
    0.06
    .community
    0.06
     trained
    0.06
     violence
    0.06
    Activations Density 0.003%

    No Known Activations