© 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. 106572
    Prev
    Next
    INDEX
    Explanations

    phrases related to police actions and justifications

    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
    aight
    -0.09
    istrovstvÃŃ
    -0.08
    iteli
    -0.08
    -caret
    -0.08
     naken
    -0.07
    pagesize
    -0.07
    .invokeLater
    -0.07
    λμ
    -0.07
    骨
    -0.07
    ramework
    -0.07
    POSITIVE LOGITS
    0.07
     pat
    0.06
     t
    0.06
     radio
    0.06
     duties
    0.06
     duty
    0.05
     Nag
    0.05
     prudent
    0.05
    olf
    0.05
     HOL
    0.05
    Activations Density 0.014%

    No Known Activations