© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 63147
    Prev
    Next
    INDEX
    Explanations

    legal terms related to income and taxation

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     bystand
    -0.06
     shorts
    -0.06
    ãĥ¡
    -0.06
     Wenger
    -0.05
    缮
    -0.05
     dorm
    -0.05
    Pool
    -0.05
     pool
    -0.05
    ÑĪин
    -0.05
    asio
    -0.05
    POSITIVE LOGITS
    ImageContext
    0.08
     kred
    0.07
    NewProp
    0.07
    .Guna
    0.07
    .SizeType
    0.07
    OffsetTable
    0.07
    oons
    0.07
    ÏĦÏį
    0.07
     Lage
    0.07
    URLException
    0.06
    Activations Density 0.025%

    No Known Activations