© 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. 56664
    Prev
    Next
    INDEX
    Explanations

    financial performance metrics and 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
     migration
    -0.06
    lyph
    -0.06
    iek
    -0.06
    inski
    -0.06
    affle
    -0.06
    ries
    -0.06
    ashed
    -0.06
    ieu
    -0.06
    205
    -0.06
    215
    -0.06
    POSITIVE LOGITS
     sales
    0.08
    -sales
    0.07
    kil
    0.07
     units
    0.07
     Sales
    0.07
    .production
    0.07
    åįķä½į
    0.07
     Goods
    0.07
    sales
    0.07
     Amateur
    0.07
    Activations Density 0.018%

    No Known Activations