© 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. 1840
    Prev
    Next
    INDEX
    Explanations

    terms related to governance and accountability in relation to corruption

    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
    .nano
    -0.08
    ndl
    -0.08
    arrant
    -0.07
    etu
    -0.07
    ieres
    -0.07
     NotImplemented
    -0.07
    sek
    -0.06
    Có
    -0.06
    mé
    -0.06
     Gratis
    -0.06
    POSITIVE LOGITS
     corruption
    0.18
     Corruption
    0.18
     corrupt
    0.15
     Transparency
    0.12
    èħIJ
    0.12
     corrupted
    0.12
     graft
    0.11
     transparent
    0.10
     Integrity
    0.10
     transparency
    0.09
    Activations Density 0.079%

    No Known Activations