© 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. 9-LLAMASCOPE-RES-131K
    11. 99082
    Prev
    Next
    INDEX
    Explanations

    numbers and numerical patterns

    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
    628
    -0.07
    ayer
    -0.07
    ÏħÏĦÏĮ
    -0.07
    ichel
    -0.07
    ricks
    -0.06
    بÙĪد
    -0.06
    uteur
    -0.06
    нг
    -0.06
    о
    -0.06
    AUSE
    -0.06
    POSITIVE LOGITS
    eenth
    0.08
    yt
    0.07
    acious
    0.07
    infeld
    0.07
    erez
    0.07
    tah
    0.07
    eding
    0.07
    OrCreate
    0.06
    érica
    0.06
    ATIO
    0.06
    Activations Density 0.187%

    No Known Activations