© 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. 86129
    Prev
    Next
    INDEX
    Explanations

    instances of formatting or structural elements in text documents

    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
    erson
    -0.07
    imet
    -0.07
    tro
    -0.06
     alot
    -0.06
     secondary
    -0.06
    lando
    -0.06
    EG
    -0.05
    oras
    -0.05
    uter
    -0.05
    dde
    -0.05
    POSITIVE LOGITS
    -FIRST
    0.08
     Já
    0.07
    izyon
    0.07
    Ìī
    0.07
    (=)
    0.07
    quake
    0.07
    _DM
    0.07
    Ð®ÐĽ
    0.07
    ivé
    0.07
     hala
    0.07
    Activations Density 0.038%

    No Known Activations