© 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. 75940
    Prev
    Next
    INDEX
    Explanations

    terms related to medical malpractice and related legal proceedings

    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
    emean
    -0.06
     lúc
    -0.06
     appellate
    -0.06
     Bald
    -0.06
    contri
    -0.06
    iveau
    -0.06
     Kitt
    -0.06
    ens
    -0.06
    iel
    -0.06
     courtroom
    -0.06
    POSITIVE LOGITS
     properly
    0.09
     Proper
    0.08
    proper
    0.08
    zik
    0.06
    ORT
    0.06
     proper
    0.06
    ascript
    0.06
    ToWorld
    0.06
     Halk
    0.06
     correctly
    0.06
    Activations Density 0.057%

    No Known Activations