© 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. 124556
    Prev
    Next
    INDEX
    Explanations

    references to foundational concepts and frameworks in scientific research

    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
     newly
    -0.07
     new
    -0.07
     could
    -0.07
    æĸ°çļĦ
    -0.06
     potentially
    -0.06
     Could
    -0.06
     Ramp
    -0.06
     future
    -0.06
     hopefully
    -0.06
    éijij
    -0.06
    POSITIVE LOGITS
    пÑĢиклад
    0.08
     famously
    0.08
     decades
    0.08
    ÏĦÏħ
    0.07
    _known
    0.07
    izzy
    0.07
    ãĥ¼ãĥĬ
    0.07
    以æĿ¥
    0.07
     widely
    0.07
    legacy
    0.07
    Activations Density 0.026%

    No Known Activations