© 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. 84176
    Prev
    Next
    INDEX
    Explanations

    concepts related to cost savings and financial advantages

    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
    uchos
    -0.07
    interopRequire
    -0.06
    enser
    -0.06
    ia
    -0.06
    rát
    -0.06
    ắng
    -0.06
     {?>↵
    -0.06
    erate
    -0.06
    illion
    -0.06
    -dropdown
    -0.06
    POSITIVE LOGITS
     comparison
    0.07
    nett
    0.07
     cost
    0.07
    .cost
    0.07
     Comparison
    0.07
     savings
    0.07
    Comparison
    0.07
    cost
    0.07
     comparative
    0.07
     Cost
    0.07
    Activations Density 0.012%

    No Known Activations