© 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. 1393
    Prev
    Next
    INDEX
    Explanations

    situations involving threats and false information

    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
     spying
    -0.07
    rdf
    -0.06
     scand
    -0.06
    Recognition
    -0.06
     serg
    -0.06
    olie
    -0.06
    åľ³
    -0.06
    éĥİ
    -0.06
     stealth
    -0.06
     uncont
    -0.06
    POSITIVE LOGITS
     threats
    0.08
     threat
    0.08
    argar
    0.08
    DCALL
    0.08
    kuk
    0.07
    xiety
    0.07
     Jub
    0.07
    gran
    0.07
    dark
    0.07
    flammatory
    0.07
    Activations Density 0.003%

    No Known Activations