© 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. 38982
    Prev
    Next
    INDEX
    Explanations

    concepts related to systemic issues and inefficiencies in governance and bureaucracies

    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
     Äijang
    -0.10
     now
    -0.09
    icast
    -0.09
    æŃ£åľ¨
    -0.09
     ÑĤепеÑĢÑĮ
    -0.08
    asher
    -0.08
     NOW
    -0.08
     ÅŁimdi
    -0.07
     à¤īसन
    -0.07
     maintenant
    -0.07
    POSITIVE LOGITS
     often
    0.20
    often
    0.17
     usually
    0.15
     Often
    0.14
     tends
    0.14
     tend
    0.14
     sometimes
    0.13
    Often
    0.13
     souvent
    0.13
     tended
    0.12
    Activations Density 0.045%

    No Known Activations