© 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. 119200
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to legal processes and court 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
    IMPLEMENT
    -0.07
    shall
    -0.06
    Fabric
    -0.06
    ersiz
    -0.06
     Fabric
    -0.06
     prank
    -0.06
    morgan
    -0.06
     Brennan
    -0.06
     ÙĤرارد
    -0.06
     Alley
    -0.06
    POSITIVE LOGITS
     gaat
    0.07
    lit
    0.07
     court
    0.07
     DefaultValue
    0.06
     trial
    0.06
    å»·
    0.06
     formal
    0.06
    /testify
    0.06
    arl
    0.06
    ucch
    0.06
    Activations Density 0.020%

    No Known Activations