© 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. 62012
    Prev
    Next
    INDEX
    Explanations

    references to specific scientific articles or studies related to medical 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
    itzer
    -0.07
    «ĺ
    -0.07
    stoff
    -0.07
    raci
    -0.07
    ниÑĨа
    -0.07
    ó
    -0.07
    اص
    -0.07
    ccak
    -0.07
     paramMap
    -0.07
    iversit
    -0.07
    POSITIVE LOGITS
    eniz
    0.06
    repid
    0.06
     ØŃض
    0.06
     gr
    0.06
    ARP
    0.06
     vag
    0.06
    меÑĪ
    0.05
     magn
    0.05
     count
    0.05
     second
    0.05
    Activations Density 0.001%

    No Known Activations