© 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. 27252
    Prev
    Next
    INDEX
    Explanations

    references to learning experiences or lessons derived from various subjects

    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
    assa
    -0.06
    elib
    -0.06
    Marsh
    -0.06
    itor
    -0.06
    oku
    -0.06
    anz
    -0.06
    oui
    -0.06
    elman
    -0.06
    sic
    -0.06
    acet
    -0.06
    POSITIVE LOGITS
     lessons
    0.14
     lesson
    0.13
     Lessons
    0.13
     Lesson
    0.11
    lessons
    0.11
    Lesson
    0.10
    lesson
    0.10
     ÑĥÑĢок
    0.10
    .lesson
    0.09
    (ins
    0.07
    Activations Density 0.018%

    No Known Activations