© 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. 71993
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to court cases and convictions

    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
     NEGLIGENCE
    -0.06
     Pret
    -0.06
     Jud
    -0.06
    tern
    -0.06
     tort
    -0.06
    AccessType
    -0.05
     lawsuits
    -0.05
    831
    -0.05
     Civil
    -0.05
     civil
    -0.05
    POSITIVE LOGITS
    XHR
    0.08
    ãĥ¼ãĥį
    0.07
    viso
    0.07
    anlı
    0.07
    eking
    0.07
     ÑģÑĤаÑĤи
    0.07
    kö
    0.07
    oreach
    0.07
    ÑĤÑı
    0.07
     Tarihi
    0.07
    Activations Density 0.024%

    No Known Activations