© 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 EvalsExportsAPI 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. 126704
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement and police personnel

    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
    ëį°ìĿ´íĬ¸
    -0.09
    çĻ»
    -0.08
    argo
    -0.08
    ascript
    -0.08
    STALL
    -0.08
    živ
    -0.08
    romÄĽ
    -0.08
    kud
    -0.08
    ehler
    -0.08
    uye
    -0.08
    POSITIVE LOGITS
     police
    0.08
     Police
    0.07
    Police
    0.07
     shift
    0.06
     visible
    0.06
     t
    0.06
     RCMP
    0.05
    ics
    0.05
     canine
    0.05
     law
    0.05
    Activations Density 0.012%

    No Known Activations