© 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. 14095
    Prev
    Next
    INDEX
    Explanations

    terms related to sufficiency and abundance

    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
    Å¡ak
    -0.09
    ικη
    -0.07
    .magic
    -0.07
    insn
    -0.07
    oola
    -0.07
    avir
    -0.07
    ียà¸Ļà¸ļ
    -0.07
    /rs
    -0.07
    /unit
    -0.07
    ιαν
    -0.06
    POSITIVE LOGITS
     entire
    0.10
     enough
    0.08
     Entire
    0.07
     several
    0.07
     twice
    0.07
     whole
    0.07
     multiple
    0.07
     sufficient
    0.06
    ultiple
    0.06
     equivalent
    0.06
    Activations Density 0.040%

    No Known Activations