© 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. 14301
    Prev
    Next
    INDEX
    Explanations

    expressions of faith and spirituality related to personal testimony and communal values

    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
    okie
    -0.07
    енз
    -0.07
    icontrol
    -0.07
    irá
    -0.07
    duc
    -0.07
    çĻ¾
    -0.07
    ProgressHUD
    -0.07
    inet
    -0.07
    .Elapsed
    -0.06
    addon
    -0.06
    POSITIVE LOGITS
     Christian
    0.07
     Christ
    0.07
     Christians
    0.07
     modelling
    0.06
    auth
    0.06
     modeling
    0.06
     living
    0.06
     Martha
    0.06
     Kingdom
    0.06
     Jesus
    0.06
    Activations Density 0.062%

    No Known Activations