© 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. 106501
    Prev
    Next
    INDEX
    Explanations

    mentions of law enforcement activities and surveillance

    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
     Bilim
    -0.09
    ardu
    -0.09
     spoilers
    -0.08
    оген
    -0.08
    jong
    -0.08
    styl
    -0.07
    شتÙĩ
    -0.07
     Ùħرک
    -0.07
    aeper
    -0.07
    ุม
    -0.07
    POSITIVE LOGITS
     facial
    0.10
     Facial
    0.07
     police
    0.07
    0.07
     use
    0.07
     racial
    0.07
     public
    0.06
     vendor
    0.06
     pat
    0.06
     Public
    0.06
    Activations Density 0.003%

    No Known Activations