© 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. 86227
    Prev
    Next
    INDEX
    Explanations

    references to waste and inefficiency in processes

    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
     immunity
    -0.07
     raz
    -0.06
    vic
    -0.06
    _EXPORT
    -0.05
    amo
    -0.05
     Outstanding
    -0.05
     bombard
    -0.05
     Santa
    -0.05
    Vect
    -0.05
    å·Ŀ
    -0.05
    POSITIVE LOGITS
     waste
    0.24
     Waste
    0.21
     wasted
    0.21
     wast
    0.21
     wasting
    0.19
     wastes
    0.18
    浪
    0.17
     unused
    0.11
     lã
    0.11
    -unused
    0.10
    Activations Density 0.124%

    No Known Activations