© 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. 116884
    Prev
    Next
    INDEX
    Explanations

    phrases associated with law enforcement and police statistics

    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
    quisition
    -0.07
    anches
    -0.07
    uye
    -0.06
    raki
    -0.06
    ObjectContext
    -0.06
    NSObject
    -0.06
    ogui
    -0.06
    rouw
    -0.06
    resident
    -0.06
    irates
    -0.06
    POSITIVE LOGITS
     LOD
    0.07
     retirement
    0.07
     fitness
    0.07
     retire
    0.07
     IA
    0.06
     exon
    0.06
    Fitness
    0.06
     training
    0.06
    Training
    0.06
    fitness
    0.06
    Activations Density 0.016%

    No Known Activations