© 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. 31559
    Prev
    Next
    INDEX
    Explanations

    processes related to feeding and energy requirements in organisms

    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
    omik
    -0.06
    -archive
    -0.06
     Dart
    -0.06
     Äijá»Ļt
    -0.06
    vs
    -0.06
    _firestore
    -0.06
    edia
    -0.06
     cầm
    -0.06
    isia
    -0.06
    idot
    -0.05
    POSITIVE LOGITS
    OMEM
    0.07
    Internal
    0.07
    /Internal
    0.07
    apesh
    0.07
    internal
    0.07
     Vacation
    0.07
    ÏĢη
    0.07
    ĶåĽŀ
    0.06
    oen
    0.06
    AIT
    0.06
    Activations Density 0.003%

    No Known Activations