© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 27039
    Prev
    Next
    INDEX
    Explanations

    monetary values and their comparisons in a financial context

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    udget
    -0.07
    ứng
    -0.07
    bage
    -0.07
    езд
    -0.06
    egov
    -0.06
    ayar
    -0.06
    arrants
    -0.06
    diag
    -0.06
    _detach
    -0.06
    ìm
    -0.06
    POSITIVE LOGITS
     DataView
    0.06
    ãĥ³ãĤ°ãĥ«
    0.06
     listings
    0.06
    _Find
    0.06
    iou
    0.06
     Colin
    0.06
    -danger
    0.06
    ako
    0.05
     masc
    0.05
    -Col
    0.05
    Activations Density 0.002%

    No Known Activations