© 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 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. 88406
    Prev
    Next
    INDEX
    Explanations

    phrases related to insider trading and stock transactions

    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
    icari
    -0.08
    .DropDown
    -0.08
    ĶåĽŀ
    -0.08
    оÑĩÑĮ
    -0.08
    ä¾
    -0.07
    _OW
    -0.07
    gili
    -0.07
    anie
    -0.07
    .CommandType
    -0.07
    endas
    -0.07
    POSITIVE LOGITS
    empl
    0.06
    aku
    0.06
     enth
    0.06
     recent
    0.06
    e
    0.05
    isper
    0.05
    -describedby
    0.05
    lit
    0.05
     judgement
    0.05
    Executor
    0.05
    Activations Density 0.000%

    No Known Activations