© 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. 15-LLAMASCOPE-RES-131K
    11. 86328
    Prev
    Next
    INDEX
    Explanations

    phrases related to stress relief and mental well-being

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    utin
    -0.06
    Ñıн
    -0.06
    etu
    -0.06
    peed
    -0.06
    dy
    -0.06
     pager
    -0.06
    anj
    -0.06
     peer
    -0.06
    peer
    -0.06
     Drinking
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.08
    eview
    0.07
     outlook
    0.07
    LOPT
    0.07
    entrant
    0.07
    asso
    0.06
    .UnitTesting
    0.06
    ·æĸ°
    0.06
    esk
    0.06
    Interop
    0.06
    Activations Density 0.014%

    No Known Activations