© 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. 85465
    Prev
    Next
    INDEX
    Explanations

    references to legal documents, specifically patents and publications

    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
    350
    -0.08
    dateFormat
    -0.06
    oma
    -0.06
    å¶
    -0.06
    achs
    -0.06
    rego
    -0.06
    encers
    -0.06
    720
    -0.06
    agan
    -0.06
    582
    -0.06
    POSITIVE LOGITS
    woord
    0.06
    amed
    0.06
     patent
    0.06
    èįī
    0.06
    ubbo
    0.06
    /doc
    0.06
    utilus
    0.06
    ToLocal
    0.06
    éĥİ
    0.06
     Kemal
    0.06
    Activations Density 0.058%

    No Known Activations