© 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. 121634
    Prev
    Next
    INDEX
    Explanations

    references to criminal activity and investigations

    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
    rex
    -0.08
    638
    -0.07
    PLE
    -0.07
    (MenuItem
    -0.06
     labels
    -0.06
     rem
    -0.06
    OLUMN
    -0.06
    orgia
    -0.06
    .labels
    -0.06
    olon
    -0.06
    POSITIVE LOGITS
     Mov
    0.07
     locations
    0.07
     movements
    0.07
    Mov
    0.07
     location
    0.07
     whereabouts
    0.07
    activity
    0.06
     activity
    0.06
    riter
    0.06
    locations
    0.06
    Activations Density 0.010%

    No Known Activations