© 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. 9-LLAMASCOPE-RES-131K
    11. 95900
    Prev
    Next
    INDEX
    Explanations

    references to attendance and restrictions regarding public events

    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
     Mattis
    -0.07
     porr
    -0.06
     kol
    -0.06
    kas
    -0.06
    ousel
    -0.06
    ainen
    -0.06
     Collision
    -0.06
    اث
    -0.06
     Suff
    -0.06
    YSIS
    -0.06
    POSITIVE LOGITS
    usher
    0.07
    stå
    0.06
    erdale
    0.06
    lest
    0.06
    ziej
    0.06
    partial
    0.06
     Humb
    0.06
    uyá»ĩn
    0.06
    Å¡ti
    0.06
     Baker
    0.06
    Activations Density 0.006%

    No Known Activations