© 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. 89672
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to convictions and serious crimes

    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
    889
    -0.08
     вÑĩ
    -0.07
    loquent
    -0.07
     yesterday
    -0.07
    frauen
    -0.07
    arrass
    -0.07
     Yates
    -0.07
     suic
    -0.07
    ër
    -0.07
     Yesterday
    -0.07
    POSITIVE LOGITS
    aker
    0.06
    edar
    0.06
    ett
    0.06
    _PTR
    0.06
     charge
    0.06
    ood
    0.06
     uptime
    0.06
    0.05
    acas
    0.05
     spor
    0.05
    Activations Density 0.012%

    No Known Activations