© 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 EvalsExportsinterp-engineNEWAPI 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. 95600
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and issues involving lawsuits

    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
    uder
    -0.07
    .scalablytyped
    -0.07
    amina
    -0.07
    thane
    -0.07
    letcher
    -0.07
    aption
    -0.07
    ieren
    -0.07
    retch
    -0.07
    GST
    -0.07
     ÙħÙĨØ·
    -0.07
    POSITIVE LOGITS
     injury
    0.10
     compensation
    0.10
     Injury
    0.10
     Compensation
    0.09
     mes
    0.09
     injuries
    0.08
     injured
    0.08
     accident
    0.08
     damages
    0.07
     victim
    0.07
    Activations Density 0.082%

    No Known Activations