© 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 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. 29066
    Prev
    Next
    INDEX
    Explanations

    C++ syntax elements related to memory management or references

    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
    ucher
    -0.07
     cuales
    -0.07
    lectron
    -0.07
    abwe
    -0.07
    tÃŃ
    -0.07
    itler
    -0.07
    iversite
    -0.07
     voks
    -0.07
    ίκ
    -0.07
    "struct
    -0.07
    POSITIVE LOGITS
    agi
    0.07
    enal
    0.07
    amp
    0.06
    i
    0.06
    asu
    0.06
     copy
    0.06
    .dst
    0.05
    789
    0.05
    ï¸ı
    0.05
     daylight
    0.05
    Activations Density 0.006%

    No Known Activations