© 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. 41303
    Prev
    Next
    INDEX
    Explanations

    numeric values and statistics related to economic indicators

    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
    antal
    -0.08
     bulk
    -0.07
    halten
    -0.07
    ãĥ³ãĤº
    -0.07
    èĪĮ
    -0.06
    عÙĦ
    -0.06
    bulk
    -0.06
    ¼åIJĪ
    -0.06
    pch
    -0.06
    clas
    -0.06
    POSITIVE LOGITS
    358
    0.06
    ÙĪار
    0.06
    tw
    0.06
    çģ
    0.06
     Econ
    0.06
     household
    0.06
     twice
    0.06
    attery
    0.06
     Martins
    0.06
    below
    0.06
    Activations Density 0.019%

    No Known Activations