© 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. 38203
    Prev
    Next
    INDEX
    Explanations

    procedures related to data entry and organization in a user interface

    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
    ring
    -0.07
     resisted
    -0.06
    ell
    -0.06
     van
    -0.06
    ze
    -0.06
    ign
    -0.06
     vans
    -0.06
    combe
    -0.06
    r
    -0.06
     sign
    -0.06
    POSITIVE LOGITS
    bish
    0.08
     âĹĦ
    0.07
    intColor
    0.07
     Obrázky
    0.07
    apons
    0.07
    undos
    0.07
    orthand
    0.07
    astos
    0.07
    eniable
    0.07
    ENU
    0.07
    Activations Density 0.001%

    No Known Activations