© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 118242
    Prev
    Next
    INDEX
    Explanations

    references to governmental plans and their impact on the population regarding benefits

    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
    agma
    -0.07
    aign
    -0.07
    ivic
    -0.06
    verbatim
    -0.06
    afd
    -0.06
    =req
    -0.06
    orrow
    -0.06
     pension
    -0.06
     Warranty
    -0.06
    sockets
    -0.06
    POSITIVE LOGITS
     households
    0.07
     Bram
    0.07
    heimer
    0.07
     families
    0.07
     Fur
    0.06
    ville
    0.06
    ê·¹
    0.06
     modest
    0.06
     Lime
    0.06
    Criterion
    0.06
    Activations Density 0.002%

    No Known Activations