© 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. 38206
    Prev
    Next
    INDEX
    Explanations

    descriptors related to comfort and sensation

    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
    otor
    -0.07
    èm
    -0.06
    ouden
    -0.06
    addtogroup
    -0.06
     Mess
    -0.06
    wit
    -0.06
    adol
    -0.06
    555
    -0.06
     Reconstruction
    -0.06
     amp
    -0.06
    POSITIVE LOGITS
    Feels
    0.11
     feels
    0.09
     feel
    0.09
     feeling
    0.08
    Feel
    0.07
     felt
    0.07
    -fe
    0.07
    ÃŃnÄĽ
    0.07
    feel
    0.07
     Feel
    0.07
    Activations Density 0.022%

    No Known Activations