© 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. 116409
    Prev
    Next
    INDEX
    Explanations

    references to fabricated or invented events and the planning involved in deception

    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
    üçük
    -0.06
    aign
    -0.06
     Cath
    -0.06
     collectors
    -0.06
     célib
    -0.06
    /maps
    -0.06
     kvin
    -0.06
     collecting
    -0.06
    ÙIJب
    -0.06
    ispers
    -0.06
    POSITIVE LOGITS
     artificial
    0.14
     Artificial
    0.12
     artificially
    0.10
     nonexistent
    0.10
     invented
    0.10
    -created
    0.10
     synthetic
    0.09
     created
    0.09
     invent
    0.09
    -create
    0.09
    Activations Density 0.093%

    No Known Activations