© 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. 99099
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of polarization in the context of electromagnetic waves

    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
    .GridView
    -0.08
    itele
    -0.07
    erce
    -0.07
    plug
    -0.07
    uses
    -0.07
    elier
    -0.07
    ansen
    -0.07
    ArgumentException
    -0.07
    ixels
    -0.06
    lili
    -0.06
    POSITIVE LOGITS
    lep
    0.06
    YN
    0.06
     spinning
    0.06
    Ï
    0.06
    stre
    0.06
    رÛĮÙģ
    0.06
    UNKNOWN
    0.05
    bee
    0.05
    edo
    0.05
     Vern
    0.05
    Activations Density 0.008%

    No Known Activations