© 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. 17066
    Prev
    Next
    INDEX
    Explanations

    references to execution processes and commands

    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
    akin
    -0.09
    indow
    -0.08
    arde
    -0.07
    ÏĢοÏħ
    -0.07
    ixo
    -0.07
    oyo
    -0.07
    red
    -0.07
    öst
    -0.07
    919
    -0.06
    kol
    -0.06
    POSITIVE LOGITS
    ables
    0.07
    ante
    0.07
     eslint
    0.07
    Ubergraph
    0.07
    icut
    0.07
    liner
    0.07
    able
    0.07
    isable
    0.07
    ÛĮا
    0.06
     Garn
    0.06
    Activations Density 0.016%

    No Known Activations