© 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. 119665
    Prev
    Next
    INDEX
    Explanations

    topics related to health, environmental justice, and community welfare

    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
     begr
    -0.07
    opr
    -0.06
    à¥įपष
    -0.06
    enstein
    -0.06
    PELL
    -0.06
    emens
    -0.06
    piel
    -0.06
    auc
    -0.06
    raph
    -0.06
    ibbon
    -0.06
    POSITIVE LOGITS
    Vtbl
    0.07
     ÑĪлÑıÑħом
    0.07
    0.07
    745
    0.06
     inh
    0.06
     forthcoming
    0.06
    MDB
    0.06
    âĢı
    0.06
     Forever
    0.06
    ymous
    0.06
    Activations Density 0.041%

    No Known Activations