© 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. 129379
    Prev
    Next
    INDEX
    Explanations

    queries and data management terms related to optimization and performance in systems

    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
    gili
    -0.08
    mdb
    -0.08
    dum
    -0.07
    antro
    -0.07
    zer
    -0.07
    avern
    -0.07
    -fontawesome
    -0.07
    ktop
    -0.07
    irmed
    -0.06
    uges
    -0.06
    POSITIVE LOGITS
     Milky
    0.06
    /manage
    0.06
    ãĥĥãĤ·ãĥ¥
    0.06
    μή
    0.06
    \CMS
    0.06
     Stark
    0.06
     cet
    0.06
    ê²
    0.06
    wan
    0.06
    _Reset
    0.06
    Activations Density 0.054%

    No Known Activations