© 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. 15-LLAMASCOPE-RES-131K
    11. 103277
    Prev
    Next
    INDEX
    Explanations

    references to events involving presentations or performances

    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
     thing
    -0.07
    uster
    -0.07
    ught
    -0.06
    Ĺ
    -0.06
    kaar
    -0.06
    ãģĦãģ®
    -0.06
    ENOMEM
    -0.06
    ermal
    -0.06
    оÑĩной
    -0.06
    IOS
    -0.06
    POSITIVE LOGITS
    olland
    0.07
    á»ĩn
    0.07
    azzi
    0.07
    ash
    0.06
    Âłje
    0.06
    657
    0.06
    åŀ
    0.06
    iq
    0.06
     labore
    0.06
    ÑĤаж
    0.06
    Activations Density 0.021%

    No Known Activations