© 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. 104157
    Prev
    Next
    INDEX
    Explanations

    legal terms and liabilities in a document

    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
    åĨł
    -0.08
    iland
    -0.07
    okino
    -0.07
    yonel
    -0.07
    unas
    -0.07
    alous
    -0.07
    lingen
    -0.07
    ervas
    -0.07
    nothrow
    -0.07
    LETED
    -0.07
    POSITIVE LOGITS
    illez
    0.06
    ayi
    0.06
     Gul
    0.06
     sine
    0.06
    elah
    0.06
     Avery
    0.05
     lev
    0.05
    име
    0.05
    anson
    0.05
     desn
    0.05
    Activations Density 0.001%

    No Known Activations