© 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. 108965
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lean" and its variations in various contexts

    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
    endon
    -0.08
    iset
    -0.07
    zon
    -0.07
    venture
    -0.07
     Poor
    -0.07
    shell
    -0.07
    imentary
    -0.07
    ument
    -0.07
    ucer
    -0.06
    athom
    -0.06
    POSITIVE LOGITS
     leaned
    0.07
     leans
    0.07
     leaning
    0.07
     Fate
    0.07
     toward
    0.07
     fate
    0.06
     heavily
    0.06
     Synd
    0.06
    Axes
    0.06
     Fulton
    0.06
    Activations Density 0.003%

    No Known Activations