© 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. 63063
    Prev
    Next
    INDEX
    Explanations

    concepts related to optimization and mapping in algorithms

    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
    ubar
    -0.07
    ago
    -0.07
    iker
    -0.07
    (éĩij
    -0.06
    chine
    -0.06
     Gon
    -0.06
    rage
    -0.06
    amps
    -0.06
     lon
    -0.06
    Om
    -0.06
    POSITIVE LOGITS
    emarks
    0.07
    ген
    0.06
    PLL
    0.06
    uments
    0.06
    á»ĭch
    0.06
     Hizmetleri
    0.06
    BUG
    0.06
    .flat
    0.06
    estic
    0.06
    ipples
    0.06
    Activations Density 0.131%

    No Known Activations