© 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. 31212
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical concepts and theories, particularly those involving measures and spaces

    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
    .scalablytyped
    -0.07
     FactoryBot
    -0.07
    Ú©ÙĪر
    -0.07
    ãģ¤ãģ¶
    -0.06
    ORMAL
    -0.06
    :checked
    -0.06
    ôt
    -0.06
    748
    -0.06
     FactoryGirl
    -0.06
    AZY
    -0.06
    POSITIVE LOGITS
     meas
    0.08
     Fat
    0.07
     partition
    0.07
     Measures
    0.07
     events
    0.07
    _partition
    0.07
     Measure
    0.07
    Fat
    0.07
     launder
    0.07
     measures
    0.06
    Activations Density 0.053%

    No Known Activations