© 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. 116730
    Prev
    Next
    INDEX
    Explanations

    elements expressing emotional resilience and composure

    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
    aggi
    -0.07
    êu
    -0.07
    .lazy
    -0.07
    overy
    -0.07
    alach
    -0.07
     lai
    -0.06
    Opaque
    -0.06
     Op
    -0.06
    hrad
    -0.06
    essler
    -0.06
    POSITIVE LOGITS
     calm
    0.15
     calmly
    0.12
     cool
    0.11
     Ñģпок
    0.10
     calming
    0.09
     cooler
    0.08
     Cool
    0.08
    cool
    0.08
     Cooler
    0.08
     stead
    0.08
    Activations Density 0.060%

    No Known Activations