© 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. 63288
    Prev
    Next
    INDEX
    Explanations

    concepts related to spiritual embodiment and disembodiment

    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
    cock
    -0.06
    ku
    -0.06
     improvement
    -0.06
     arz
    -0.06
     bore
    -0.06
    gabe
    -0.06
    366
    -0.06
    ROID
    -0.06
     sleeping
    -0.06
     bearing
    -0.06
    POSITIVE LOGITS
    ãĥ¬ãĥ³
    0.09
    ãĥ³ãĥIJ
    0.07
     negativity
    0.07
    emoc
    0.07
     Reactive
    0.07
    oldemort
    0.07
    irected
    0.06
    ylie
    0.06
    寶
    0.06
     Negative
    0.06
    Activations Density 0.004%

    No Known Activations