© 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. 74022
    Prev
    Next
    INDEX
    Explanations

    phrases expressing the concept of wastefulness or inefficiency

    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
    elop
    -0.07
    iez
    -0.07
    Æł
    -0.06
    onto
    -0.06
     ÐĶеÑĢжав
    -0.06
     palms
    -0.06
    chein
    -0.06
    presso
    -0.06
    zos
    -0.06
    /comment
    -0.06
    POSITIVE LOGITS
     effort
    0.07
    ubo
    0.07
     resources
    0.07
     waste
    0.07
     opportunity
    0.07
    οÏħν
    0.06
    anga
    0.06
     a
    0.06
    ¾
    0.06
     an
    0.06
    Activations Density 0.004%

    No Known Activations