© 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. 124337
    Prev
    Next
    INDEX
    Explanations

    phrases related to saving resources or money

    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
    ÙħاÙĦ
    -0.07
    lamp
    -0.07
    \grid
    -0.06
    ULA
    -0.06
    shore
    -0.06
    æ£ļ
    -0.06
    hop
    -0.06
     Blow
    -0.06
    ijn
    -0.06
    amped
    -0.06
    POSITIVE LOGITS
     Saved
    0.07
     money
    0.07
     save
    0.07
    czy
    0.07
     saved
    0.07
    orer
    0.06
     saves
    0.06
    esson
    0.06
    -money
    0.06
    vron
    0.06
    Activations Density 0.003%

    No Known Activations