© 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. 15-LLAMASCOPE-RES-131K
    11. 1570
    Prev
    Next
    INDEX
    Explanations

    financial terms and concepts related to funding and income sources

    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
    stdClass
    -0.08
    eam
    -0.07
    .scalablytyped
    -0.07
    ays
    -0.07
    thon
    -0.06
    iable
    -0.06
    riter
    -0.06
    pron
    -0.06
    orda
    -0.06
    èĤ¡ä¸ľ
    -0.06
    POSITIVE LOGITS
     sale
    0.10
     sell
    0.09
     selling
    0.08
     sales
    0.08
    jualan
    0.08
     sold
    0.08
    åįĸ
    0.08
     sells
    0.07
    -selling
    0.07
     venda
    0.07
    Activations Density 0.147%

    No Known Activations