© 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. 5776
    Prev
    Next
    INDEX
    Explanations

    elements related to duality, particularly involving the mind, body, and spirit

    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
     inex
    -0.06
    empl
    -0.06
    daf
    -0.06
     Bank
    -0.06
    .Rotate
    -0.06
    -src
    -0.06
     Fog
    -0.06
    ENTA
    -0.06
    actories
    -0.06
    lage
    -0.05
    POSITIVE LOGITS
     travel
    0.14
     transportation
    0.13
     transport
    0.13
     traveling
    0.12
     road
    0.12
    Transport
    0.11
    transport
    0.11
     Transportation
    0.11
     travelling
    0.11
    travel
    0.11
    Activations Density 0.123%

    No Known Activations