© 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. 31491
    Prev
    Next
    INDEX
    Explanations

    aspects of immersive listening experiences and preferences for audio formats

    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
    letal
    -0.07
    ippo
    -0.06
    ijd
    -0.06
    usra
    -0.06
    opal
    -0.06
     Pg
    -0.06
    chem
    -0.06
     must
    -0.06
    allis
    -0.06
    .must
    -0.06
    POSITIVE LOGITS
     fewer
    0.10
    asier
    0.08
     easier
    0.08
    better
    0.08
     fres
    0.08
     THEN
    0.07
    ãĥĥãĥĪ
    0.07
    ãĥªãĤ¹
    0.07
     moins
    0.07
     better
    0.07
    Activations Density 0.129%

    No Known Activations