© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 55019
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement and criminal investigations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ãģİ
    -0.07
    길
    -0.06
    umbs
    -0.06
    .googlecode
    -0.06
    PACE
    -0.06
    PEC
    -0.06
    ç«
    -0.06
    iola
    -0.06
    лÑı
    -0.06
    ãĤ
    -0.06
    POSITIVE LOGITS
     district
    0.10
     District
    0.08
    district
    0.08
     police
    0.07
    District
    0.07
     local
    0.07
     locally
    0.06
     station
    0.06
    istrict
    0.06
     districts
    0.06
    Activations Density 0.010%

    No Known Activations