© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 87242
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions and market conditions

    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
     Har
    -0.06
    ekil
    -0.06
    oli
    -0.06
    tü
    -0.06
    akin
    -0.06
    žen
    -0.06
    äter
    -0.05
    ucs
    -0.05
    oya
    -0.05
    nick
    -0.05
    POSITIVE LOGITS
    ãĥ¼ãĥĩ
    0.07
    illard
    0.07
    .obtain
    0.07
    æľĢè¿ij
    0.07
     collar
    0.07
    彩票
    0.07
    unsch
    0.07
    Lite
    0.07
     пÑĢим
    0.07
    CORD
    0.06
    Activations Density 0.010%

    No Known Activations