© 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. 1483
    Prev
    Next
    INDEX
    Explanations

    methods related to setting up and tearing down test cases in coding environments

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    owi
    -0.05
    holm
    -0.05
     misplaced
    -0.05
     sn
    -0.05
    aylight
    -0.05
     Ch
    -0.05
     Pod
    -0.05
     Tropical
    -0.05
    á»Ļ
    -0.05
     Mohammad
    -0.05
    POSITIVE LOGITS
    .Bounds
    0.08
     rowspan
    0.07
    antom
    0.07
    erox
    0.07
    urch
    0.07
    peater
    0.07
    æ²ī
    0.07
     دÙģتر
    0.07
    okud
    0.06
    pector
    0.06
    Activations Density 0.000%

    No Known Activations