© 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. 73575
    Prev
    Next
    INDEX
    Explanations

    references to intelligence and complex systems, particularly in relation to life

    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
     reinc
    -0.07
    lias
    -0.07
    emento
    -0.06
    nech
    -0.06
     unh
    -0.06
    ensi
    -0.06
    _pb
    -0.06
    709
    -0.06
    ornings
    -0.06
    476
    -0.06
    POSITIVE LOGITS
    /design
    0.07
    addy
    0.06
    irected
    0.06
    ноÑĪ
    0.06
    chai
    0.06
     çŁ
    0.06
     sperma
    0.06
    ivid
    0.06
     designer
    0.06
    eced
    0.06
    Activations Density 0.003%

    No Known Activations