© 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. 27069
    Prev
    Next
    INDEX
    Explanations

    concepts related to spiritual perception and experience

    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
     Seal
    -0.06
    nic
    -0.06
    etting
    -0.06
    dur
    -0.06
     Hell
    -0.06
    عب
    -0.06
     Hyde
    -0.06
     Mr
    -0.06
    incinn
    -0.06
    arc
    -0.06
    POSITIVE LOGITS
     eyes
    0.13
    eyes
    0.11
     vision
    0.11
     sight
    0.11
     eye
    0.11
     Eyes
    0.11
    -eye
    0.10
    Eye
    0.09
     viewing
    0.09
    seeing
    0.09
    Activations Density 0.057%

    No Known Activations