© 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. 56192
    Prev
    Next
    INDEX
    Explanations

    phrases related to investment and financial planning

    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
    argin
    -0.07
    ihu
    -0.07
    ÑĢÑİ
    -0.06
     ØŃÙĪزÙĩ
    -0.06
    zl
    -0.06
     Licensing
    -0.06
     Fixture
    -0.06
     PartialView
    -0.06
    vell
    -0.06
    oub
    -0.06
    POSITIVE LOGITS
     selections
    0.08
     Pointer
    0.07
     choices
    0.07
    ·»
    0.07
     option
    0.07
     choice
    0.07
     options
    0.07
     offered
    0.07
    choice
    0.07
    Tracks
    0.07
    Activations Density 0.003%

    No Known Activations