© 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. 86125
    Prev
    Next
    INDEX
    Explanations

    key terms associated with transactions and financial processes

    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
     oltre
    -0.07
    ilan
    -0.07
    WEEN
    -0.06
     ë¿IJ
    -0.06
    âĹıâĹıâĹıâĹı
    -0.06
    ropy
    -0.06
    pies
    -0.06
    roys
    -0.06
    aly
    -0.06
    å£
    -0.06
    POSITIVE LOGITS
     similarly
    0.16
     likewise
    0.13
     ebenfalls
    0.12
     Similarly
    0.12
     equally
    0.11
    Similarly
    0.11
     zase
    0.10
    åīĩ
    0.10
     naopak
    0.10
    dit
    0.10
    Activations Density 0.005%

    No Known Activations