© 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. 4351
    Prev
    Next
    INDEX
    Explanations

    references to court decisions and 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
    istrovstvÃŃ
    -0.08
    æĿī
    -0.07
    Ñĸон
    -0.07
    enia
    -0.07
    enstein
    -0.07
    ONO
    -0.06
    ardon
    -0.06
    ValuePair
    -0.06
    oui
    -0.06
    yonel
    -0.06
    POSITIVE LOGITS
    umann
    0.06
     reasoning
    0.06
    ustum
    0.06
     conclusion
    0.06
     condition
    0.06
     route
    0.06
     concluded
    0.05
    sl
    0.05
    sworth
    0.05
     concludes
    0.05
    Activations Density 0.019%

    No Known Activations