© 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. 125128
    Prev
    Next
    INDEX
    Explanations

    recurring articles in Dutch text

    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
    iec
    -0.08
    htable
    -0.07
    de
    -0.07
    azu
    -0.06
    ies
    -0.06
     Sm
    -0.06
     de
    -0.06
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    -0.06
    elligence
    -0.06
    tra
    -0.06
    POSITIVE LOGITS
    ese
    0.09
    avanaugh
    0.07
    ëł´
    0.07
    jen
    0.07
    ERCHANT
    0.07
    itler
    0.07
    VICES
    0.07
    acers
    0.07
    imit
    0.06
    Å¡ak
    0.06
    Activations Density 0.003%

    No Known Activations