© 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. 130489
    Prev
    Next
    INDEX
    Explanations

    concepts related to inefficiency or productivity loss

    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
     doz
    -0.06
    berapa
    -0.06
    å±Ĭ
    -0.06
     dine
    -0.06
    639
    -0.06
     Fuel
    -0.06
    threshold
    -0.06
    OTE
    -0.05
     nuisance
    -0.05
     ener
    -0.05
    POSITIVE LOGITS
     Bever
    0.07
     çı
    0.07
    FRING
    0.07
    oki
    0.07
    PERT
    0.06
    endars
    0.06
     Customers
    0.06
    //{{
    0.06
     Paras
    0.06
     CAUSED
    0.06
    Activations Density 0.000%

    No Known Activations