© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 71063
    Prev
    Next
    INDEX
    Explanations

    numerous mentions of events, programs, and competitions within a structured or organizational context

    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
    itz
    -0.07
    年代
    -0.07
     themselves
    -0.06
    алов
    -0.06
    eydi
    -0.06
     Ùħتر
    -0.06
     Franti
    -0.06
    stra
    -0.06
    yl
    -0.06
    Advisor
    -0.06
    POSITIVE LOGITS
     ÑĤÑĥ
    0.07
    ixa
    0.07
    atori
    0.06
    cka
    0.06
     ener
    0.06
    ghi
    0.06
     инÑĦоÑĢма
    0.06
    ↵
    0.06
    (click
    0.06
    nds
    0.06
    Activations Density 0.048%

    No Known Activations