© 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. 15-LLAMASCOPE-RES-131K
    11. 86230
    Prev
    Next
    INDEX
    Explanations

    code structure elements in programming languages

    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
    apesh
    -0.07
    lash
    -0.07
    emd
    -0.07
    zá
    -0.07
    loat
    -0.06
     Aur
    -0.06
    uma
    -0.06
    pics
    -0.06
    onte
    -0.06
    keterangan
    -0.06
    POSITIVE LOGITS
    über
    0.08
     FileMode
    0.07
     bleach
    0.06
     absorbed
    0.06
     +++
    0.06
     prosec
    0.06
     üz
    0.06
    .CASCADE
    0.06
     addCriterion
    0.06
     datastore
    0.06
    Activations Density 0.000%

    No Known Activations