© 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. 1205
    Prev
    Next
    INDEX
    Explanations

    elements related to supernatural and occult themes

    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
    IFO
    -0.07
    #
    -0.07
    plex
    -0.06
    rypton
    -0.06
     coquine
    -0.06
    verity
    -0.06
    urette
    -0.06
     wives
    -0.06
     PureComponent
    -0.06
     TMPro
    -0.06
    POSITIVE LOGITS
     handy
    0.07
    eten
    0.06
     ov
    0.06
    ávÄĽ
    0.06
    Callable
    0.06
    oor
    0.06
     fuck
    0.06
    ìľĦìĽIJ
    0.06
     dispose
    0.06
    .setTimeout
    0.06
    Activations Density 0.001%

    No Known Activations