© 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. 26841
    Prev
    Next
    INDEX
    Explanations

    references to organ donation

    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
     hire
    -0.07
    lyn
    -0.07
     Hire
    -0.06
    á»ģn
    -0.06
    ĵn
    -0.06
    esk
    -0.06
    readcrumbs
    -0.06
    onta
    -0.06
    .meta
    -0.06
    ÃŃsk
    -0.06
    POSITIVE LOGITS
     organ
    0.08
     death
    0.08
     deceased
    0.08
     altru
    0.08
    death
    0.07
    STEM
    0.07
     organs
    0.06
    Death
    0.06
     Death
    0.06
    æŃ»
    0.06
    Activations Density 0.018%

    No Known Activations