© 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. 31743
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emotional states or reactions

    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
     både
    -0.07
    ICTURE
    -0.07
    ìĿ´ëĤĺ
    -0.06
    âĢĮâĢĮ
    -0.06
    oun
    -0.06
    365
    -0.06
    ãģ¾ãģļ
    -0.06
     ones
    -0.06
    POINTS
    -0.06
    ÙĪÛĮÙĦ
    -0.06
    POSITIVE LOGITS
     also
    0.07
    ApiController
    0.07
    /or
    0.07
     meant
    0.06
    readcr
    0.06
    kers
    0.06
    eyen
    0.06
    edy
    0.06
    -opacity
    0.06
    ppe
    0.06
    Activations Density 0.048%

    No Known Activations