© 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. 84233
    Prev
    Next
    INDEX
    Explanations

    terminology related to government assistance programs and their mechanisms

    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
    facet
    -0.07
     رز
    -0.06
    bero
    -0.06
    ero
    -0.06
    uner
    -0.06
     extradition
    -0.06
    ær
    -0.06
     Temper
    -0.06
     wax
    -0.06
     Bray
    -0.06
    POSITIVE LOGITS
     HUD
    0.09
     Housing
    0.08
    HUD
    0.08
     housing
    0.07
     Program
    0.07
     aw
    0.07
    丸
    0.07
    оген
    0.07
     activeClassName
    0.07
     USDA
    0.07
    Activations Density 0.002%

    No Known Activations