© 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. 95956
    Prev
    Next
    INDEX
    Explanations

    phrases related to breathing techniques and relaxation

    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
    fea
    -0.07
    phem
    -0.06
    shm
    -0.06
    YD
    -0.06
    arkin
    -0.06
     stare
    -0.06
    anova
    -0.06
     Voyage
    -0.06
    owe
    -0.06
    gle
    -0.06
    POSITIVE LOGITS
     breath
    0.11
     breathing
    0.10
     Breath
    0.09
     breathe
    0.09
     breathed
    0.08
    -bre
    0.08
     respir
    0.08
     exh
    0.08
    haled
    0.08
    bre
    0.07
    Activations Density 0.009%

    No Known Activations