© 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. 96221
    Prev
    Next
    INDEX
    Explanations

    locations and states, particularly in Hawaii

    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
    .TestTools
    -0.06
    itu
    -0.06
    iris
    -0.06
    ÅĤu
    -0.05
     UNS
    -0.05
     ÏħÏĢο
    -0.05
    imp
    -0.05
    ¬
    -0.05
    á»ijt
    -0.05
     Shake
    -0.05
    POSITIVE LOGITS
    apgolly
    0.07
    بش
    0.07
    ylie
    0.07
    ©©
    0.07
    ouri
    0.06
    reau
    0.06
    .scalablytyped
    0.06
    ardown
    0.06
     Bryan
    0.06
    @Spring
    0.06
    Activations Density 0.001%

    No Known Activations