© 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. 15-LLAMASCOPE-RES-131K
    11. 86749
    Prev
    Next
    INDEX
    Explanations

    references to incidents involving police and accountability

    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
    ìķĶ
    -0.07
    ادÛĮ
    -0.06
    rift
    -0.06
     quam
    -0.06
    ultan
    -0.06
    à¹ĥà¸Ī
    -0.06
    ÛĮرÙĩ
    -0.06
    hab
    -0.06
    uder
    -0.06
    etin
    -0.06
    POSITIVE LOGITS
     EITHER
    0.07
     reported
    0.07
     either
    0.07
    andalone
    0.06
    chia
    0.06
    kers
    0.06
    itsu
    0.06
    ippi
    0.06
     Reported
    0.06
    edium
    0.06
    Activations Density 0.031%

    No Known Activations