© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 107018
    Prev
    Next
    INDEX
    Explanations

    terms related to financial accounting and tax deductions

    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
    anch
    -0.07
    ismatch
    -0.07
    inki
    -0.07
    nout
    -0.06
    kee
    -0.06
    ANCH
    -0.06
    ÏĦαÏĤ
    -0.06
    819
    -0.06
     dét
    -0.06
    зÑĥ
    -0.06
    POSITIVE LOGITS
     future
    0.07
    æµİ
    0.07
     stores
    0.06
    zsche
    0.06
     store
    0.06
    .dispose
    0.06
     transfer
    0.06
     Invent
    0.06
    fade
    0.06
     carry
    0.06
    Activations Density 0.010%

    No Known Activations