© 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. 71879
    Prev
    Next
    INDEX
    Explanations

    repeated numeric values or sequences

    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
          ↵      ↵
    -0.07
    ãĥ¼ãģ®
    -0.07
          ↵
    -0.07
    oyal
    -0.07
    idl
    -0.07
    à¸Ħวามร
    -0.07
    bons
    -0.07
    azon
    -0.07
    ÙģØ´
    -0.07
    ãģ¾ãģŁ
    -0.07
    POSITIVE LOGITS
    rops
    0.08
    rd
    0.08
    mare
    0.07
    éĿ©
    0.07
    emos
    0.07
    éĸĵ
    0.07
    UTERS
    0.06
    ually
    0.06
    urname
    0.06
     gag
    0.06
    Activations Density 0.021%

    No Known Activations