© 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. 123465
    Prev
    Next
    INDEX
    Explanations

    elements related to sorting and order within data structures

    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
    alink
    -0.09
    agram
    -0.09
    usher
    -0.08
    izmet
    -0.08
    Ĥæķ°
    -0.08
    ADIO
    -0.08
    amespace
    -0.07
    atto
    -0.07
    atron
    -0.07
     fidelity
    -0.07
    POSITIVE LOGITS
     direction
    0.09
     sorting
    0.08
     Sort
    0.07
    Direction
    0.07
     Direction
    0.07
     Sorting
    0.07
     SORT
    0.07
     directions
    0.07
    æİĴåºı
    0.07
     sort
    0.07
    Activations Density 0.005%

    No Known Activations