© 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. 59653
    Prev
    Next
    INDEX
    Explanations

    elements related to formal or technical language structures, possibly mathematical or programming contexts

    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
    Ñĥда
    -0.07
    ceb
    -0.06
    asis
    -0.06
    fos
    -0.06
     cam
    -0.06
    æķ£
    -0.06
     vin
    -0.06
    raction
    -0.06
    æĿī
    -0.06
    avana
    -0.05
    POSITIVE LOGITS
     Fibonacci
    0.10
     Fib
    0.08
    gamber
    0.07
     fib
    0.07
    fib
    0.06
     fibonacci
    0.06
     Byl
    0.06
     Rapid
    0.06
    onacci
    0.06
    STM
    0.06
    Activations Density 0.003%

    No Known Activations