© 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. 9-LLAMASCOPE-RES-131K
    11. 94812
    Prev
    Next
    INDEX
    Explanations

    references to the Australian legal and political system, including discussions of family law and government actions

    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
    rych
    -0.07
     local
    -0.07
    ihn
    -0.06
     global
    -0.06
     locally
    -0.06
    raig
    -0.06
    .construct
    -0.06
     o
    -0.06
    øj
    -0.06
    ilip
    -0.06
    POSITIVE LOGITS
    Atlantic
    0.07
    /../
    0.07
    ORMAT
    0.07
     Federal
    0.07
    kee
    0.07
    |int
    0.06
     اÙĦات
    0.06
    ÑģÑİ
    0.06
     malt
    0.06
    SqlConnection
    0.06
    Activations Density 0.043%

    No Known Activations