© 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. 29357
    Prev
    Next
    INDEX
    Explanations

    legal terms and processes, particularly relating to lawsuits and legal representation

    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
    ãĥĥãĤ«ãĥ¼
    -0.08
    eras
    -0.07
    Authority
    -0.07
    itin
    -0.07
    (Gravity
    -0.07
    atrib
    -0.07
    ajan
    -0.07
    λεκ
    -0.07
    icals
    -0.07
    erals
    -0.07
    POSITIVE LOGITS
     lawyer
    0.17
     lawyers
    0.17
     attorney
    0.15
     attorneys
    0.15
     agent
    0.14
     lawy
    0.14
     Lawyers
    0.13
     representation
    0.13
     counsel
    0.12
     Lawyer
    0.12
    Activations Density 0.163%

    No Known Activations