© 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. 59612
    Prev
    Next
    INDEX
    Explanations

    discourse related to political succession and governance

    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
    екÑĤоÑĢ
    -0.08
    istrovstvÃŃ
    -0.07
    ----------------------------------------------------------------------↵
    -0.07
    екÑĤоÑĢа
    -0.07
     belang
    -0.07
    pora
    -0.07
    cratch
    -0.07
    %f
    -0.07
    .ravel
    -0.07
     Wich
    -0.07
    POSITIVE LOGITS
     Convention
    0.07
     Cooper
    0.06
    PLL
    0.06
     either
    0.06
     scenario
    0.06
    ocos
    0.06
    then
    0.06
     then
    0.06
     tempor
    0.06
     blocks
    0.06
    Activations Density 0.004%

    No Known Activations