© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 91729
    Prev
    Next
    INDEX
    Explanations

    references to collections and artifacts in museum contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ioso
    -0.07
    моÑģ
    -0.06
     Milky
    -0.06
    _ASCII
    -0.06
    bastian
    -0.06
    islation
    -0.06
    oth
    -0.06
    оÑĢов
    -0.06
    ois
    -0.06
    .sap
    -0.06
    POSITIVE LOGITS
     museums
    0.08
     Museum
    0.07
     private
    0.07
    ardown
    0.07
     addCriterion
    0.07
    ransition
    0.07
    ecz
    0.07
    //{{
    0.07
    tsy
    0.07
     Muse
    0.07
    Activations Density 0.017%

    No Known Activations