© 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. 80637
    Prev
    Next
    INDEX
    Explanations

    references to programming languages, specifically Java

    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
    .scalablytyped
    -0.08
    ingo
    -0.07
    TL
    -0.07
    ÑŁ
    -0.07
    -lfs
    -0.07
    nob
    -0.06
    inges
    -0.06
    eyJ
    -0.06
    harma
    -0.06
    evin
    -0.06
    POSITIVE LOGITS
     inner
    0.06
     ná»Ļi
    0.06
    gii
    0.06
     BÃŃ
    0.06
    微软éĽħé»ij
    0.06
    sdale
    0.06
    _pri
    0.06
    ],[-
    0.06
    á»ī
    0.06
    ãĥł
    0.06
    Activations Density 0.000%

    No Known Activations