© 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. 82884
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to financial transactions and obligations

    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
    .gg
    -0.08
    usses
    -0.07
    chwitz
    -0.07
    å²³
    -0.06
    è¨Ĥ
    -0.06
    кав
    -0.06
    ussian
    -0.06
    982
    -0.06
    549
    -0.06
    OTE
    -0.06
    POSITIVE LOGITS
     mort
    0.07
    mort
    0.07
    backs
    0.06
     hundreds
    0.06
    -mort
    0.06
     housing
    0.06
    cased
    0.06
    oenix
    0.06
     Huntington
    0.06
     legal
    0.06
    Activations Density 0.000%

    No Known Activations