© 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. 9-LLAMASCOPE-RES-131K
    11. 95350
    Prev
    Next
    INDEX
    Explanations

    references to operating costs and expenses within financial contexts

    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
    yo
    -0.07
     Lang
    -0.07
    âĢĮÛĮ
    -0.07
    å»
    -0.06
     bef
    -0.06
    ãģĺ
    -0.06
    .ix
    -0.06
    /MIT
    -0.06
    oul
    -0.06
    ths
    -0.06
    POSITIVE LOGITS
    327
    0.08
    aux
    0.07
    iffer
    0.07
    añ
    0.07
    esa
    0.07
    ques
    0.07
    ael
    0.06
     Mattis
    0.06
    GC
    0.06
    otten
    0.06
    Activations Density 0.003%

    No Known Activations