© 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. 30261
    Prev
    Next
    INDEX
    Explanations

    phrases related to stock holdings and insider trading

    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
     RC
    -0.07
    ÙĪاء
    -0.07
    someone
    -0.06
    елик
    -0.06
    ureau
    -0.06
    elsea
    -0.06
    finity
    -0.06
    çuk
    -0.06
    RC
    -0.06
    iju
    -0.06
    POSITIVE LOGITS
    .StackTrace
    0.07
     invested
    0.06
     exerc
    0.06
     Dia
    0.06
    INET
    0.06
    .AutoSizeMode
    0.06
    ullah
    0.06
     nose
    0.06
     invest
    0.06
    rov
    0.06
    Activations Density 0.002%

    No Known Activations