© 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. 121411
    Prev
    Next
    INDEX
    Explanations

    actions related to movement and transition

    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
    etsk
    -0.07
    _APB
    -0.06
    éªĮ
    -0.06
     برابر
    -0.06
    otec
    -0.06
    368
    -0.06
    artner
    -0.06
    .infinity
    -0.06
    lant
    -0.06
    cps
    -0.06
    POSITIVE LOGITS
     âĸ¼
    0.06
    addock
    0.06
    ĶåĽŀ
    0.06
     Gum
    0.06
     er
    0.06
    kah
    0.06
     APPRO
    0.06
    ruk
    0.06
    ukes
    0.06
     Weather
    0.06
    Activations Density 0.031%

    No Known Activations