© 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. 69115
    Prev
    Next
    INDEX
    Explanations

    identifiers and status messages related to system processes or applications

    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
    achi
    -0.07
    aly
    -0.07
    avern
    -0.07
    eck
    -0.07
    yun
    -0.07
    baugh
    -0.07
    ukkan
    -0.07
    .WinForms
    -0.07
    æĹ
    -0.07
    allet
    -0.07
    POSITIVE LOGITS
    655
    0.06
     Process
    0.06
     Mü
    0.05
    ki
    0.05
     æĪ
    0.05
    (Process
    0.05
    nu
    0.05
    _Content
    0.05
     Mun
    0.05
    _PARENT
    0.05
    Activations Density 0.003%

    No Known Activations