© 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. 9-LLAMASCOPE-RES-131K
    11. 95316
    Prev
    Next
    INDEX
    Explanations

    key points related to significance and importance

    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
    ddit
    -0.08
    irie
    -0.07
     Retorna
    -0.07
    rror
    -0.07
    mdir
    -0.07
    okoj
    -0.07
    eed
    -0.07
    諸
    -0.07
    oir
    -0.07
    adir
    -0.07
    POSITIVE LOGITS
    ikan
    0.07
    /rss
    0.06
    ayer
    0.06
    erguson
    0.06
    age
    0.06
     dür
    0.06
    zon
    0.06
     Ferguson
    0.06
    hand
    0.06
    st
    0.05
    Activations Density 0.031%

    No Known Activations