© 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. 57392
    Prev
    Next
    INDEX
    Explanations

    references to various types of structures, services, or systems that involve laws and regulations

    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
    uien
    -0.08
    ï½¢
    -0.08
    .DropDown
    -0.08
    .FontStyle
    -0.08
    опÑĢи
    -0.08
    ÑĢеÑĪ
    -0.07
    ábado
    -0.07
    Ｏ
    -0.07
    ampie
    -0.07
    каÑģ
    -0.07
    POSITIVE LOGITS
     famously
    0.06
     UIResponder
    0.06
    ¤
    0.06
    628
    0.06
    142
    0.06
    DP
    0.06
     mum
    0.06
     reuseIdentifier
    0.06
    511
    0.05
    DL
    0.05
    Activations Density 0.031%

    No Known Activations