© 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. 17-LLAMASCOPE-RES-131K
    11. 77864
    Prev
    Next
    INDEX
    Explanations

    financial entities related to business and investments

    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
     personally
    -0.06
    驾
    -0.06
     III
    -0.05
    Authorities
    -0.05
    tek
    -0.05
    _SUPPORTED
    -0.05
    æľĭ
    -0.05
    _rights
    -0.05
    à¥įयवस
    -0.05
    å¼ĺ
    -0.05
    POSITIVE LOGITS
     itself
    0.10
    æĹĹ
    0.08
     its
    0.07
     sitesinde
    0.07
    omu
    0.07
    icha
    0.07
    -sponsored
    0.07
    isko
    0.07
    logo
    0.07
    GORITHM
    0.07
    Activations Density 0.003%

    No Known Activations