© 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. 91582
    Prev
    Next
    INDEX
    Explanations

    expressions and concepts related to service and self-sacrifice

    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
     ydk
    -0.07
    tal
    -0.07
    -dot
    -0.06
     uintptr
    -0.06
    ogi
    -0.06
     JpaRepository
    -0.06
    zac
    -0.06
    uisse
    -0.06
     Hatch
    -0.06
    Techn
    -0.06
    POSITIVE LOGITS
     caring
    0.11
     compassion
    0.10
     empathy
    0.09
     humanitarian
    0.09
     altru
    0.08
     charity
    0.08
    compass
    0.08
     concern
    0.07
     service
    0.07
     philanth
    0.07
    Activations Density 0.065%

    No Known Activations