© 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. 27512
    Prev
    Next
    INDEX
    Explanations

    references to artistic elements and production aspects in creative works

    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
    licken
    -0.06
     feedback
    -0.06
     usual
    -0.06
    utos
    -0.06
    voices
    -0.06
     Jag
    -0.06
    _depend
    -0.05
     meaning
    -0.05
     interp
    -0.05
     famously
    -0.05
    POSITIVE LOGITS
     lately
    0.09
    ease
    0.07
    Å¡em
    0.07
    crop
    0.07
     parece
    0.07
    Apparently
    0.07
    emet
    0.07
    Å¡i
    0.07
     apparently
    0.07
    à¸ĩศ
    0.07
    Activations Density 0.023%

    No Known Activations