© 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. 26894
    Prev
    Next
    INDEX
    Explanations

    references to illegal or controlled substances

    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
    ccione
    -0.08
    .Asset
    -0.07
     uprav
    -0.06
    اÙĤÙĦ
    -0.06
    jem
    -0.06
     volcan
    -0.06
    祥
    -0.06
     volunt
    -0.06
     basket
    -0.06
    ortex
    -0.06
    POSITIVE LOGITS
     schön
    0.07
    eso
    0.06
     chlorine
    0.06
     nackte
    0.06
     bob
    0.06
     Boo
    0.06
    paginate
    0.06
    Packages
    0.06
     contr
    0.05
     gef
    0.05
    Activations Density 0.011%

    No Known Activations