© 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. 96062
    Prev
    Next
    INDEX
    Explanations

    technical terms related to database query optimization

    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
    STEP
    -0.06
    andre
    -0.06
    ippi
    -0.06
     BDSM
    -0.06
    اء
    -0.06
    .OrderBy
    -0.06
    ody
    -0.06
    apur
    -0.06
    seau
    -0.06
     thuáºŃn
    -0.06
    POSITIVE LOGITS
    uzzy
    0.07
     bag
    0.06
     Pruitt
    0.06
    oplast
    0.06
     temporal
    0.06
     pop
    0.06
    mlink
    0.06
    Temporal
    0.06
     Extract
    0.06
    erta
    0.06
    Activations Density 0.017%

    No Known Activations