© 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 EvalsExportsinterp-engineNEWAPI 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. 73162
    Prev
    Next
    INDEX
    Explanations

    references to unsupervised training methods in the context of video prediction

    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
    лика
    -0.08
    elerini
    -0.07
    quam
    -0.07
    leurs
    -0.07
     sobie
    -0.07
     DISCLAIMER
    -0.07
    lease
    -0.07
     spoilers
    -0.07
    akes
    -0.07
     guts
    -0.07
    POSITIVE LOGITS
     learning
    0.08
     training
    0.08
    -learning
    0.08
     manner
    0.07
     fashion
    0.07
    ervised
    0.07
     trained
    0.06
    onec
    0.06
    -leaning
    0.06
    ness
    0.06
    Activations Density 0.008%

    No Known Activations