© 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. 2855
    Prev
    Next
    INDEX
    Explanations

    price-related financial terms and values

    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
    äºĨ解
    -0.06
     midd
    -0.06
    /Set
    -0.06
     Moss
    -0.06
    stag
    -0.06
     Ban
    -0.06
     Jarvis
    -0.06
     Bacon
    -0.06
    ↵↵
    -0.06
    anan
    -0.06
    POSITIVE LOGITS
    anteed
    0.07
    é«
    0.07
    antee
    0.07
    andi
    0.07
    ainer
    0.07
    ãĥ¼ãĤ¹ãĥĪ
    0.07
    uste
    0.06
    ettel
    0.06
    wor
    0.06
    alian
    0.06
    Activations Density 0.002%

    No Known Activations