© 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. 118174
    Prev
    Next
    INDEX
    Explanations

    references to specific models and terminologies in video prediction and forecasting

    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
    chai
    -0.08
    iais
    -0.07
    assis
    -0.07
    á»ı
    -0.07
    ountry
    -0.06
    adÃŃ
    -0.06
    oplay
    -0.06
     hrd
    -0.06
    aval
    -0.06
    phis
    -0.06
    POSITIVE LOGITS
    otch
    0.06
     framework
    0.06
     adlı
    0.06
    âĦ¢
    0.06
    .forRoot
    0.06
     approach
    0.06
    .GraphicsUnit
    0.06
    ewith
    0.06
    Net
    0.06
    antaged
    0.06
    Activations Density 0.059%

    No Known Activations