© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 55635
    Prev
    Next
    INDEX
    Explanations

    funding and initiatives related to health services and care improvements for underserved communities

    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
    ñana
    -0.07
    abra
    -0.07
    licher
    -0.07
    .sdk
    -0.07
    .sections
    -0.07
    .alloc
    -0.07
    expo
    -0.07
    bons
    -0.07
     virgin
    -0.06
    abr
    -0.06
    POSITIVE LOGITS
    yre
    0.07
    oden
    0.06
    426
    0.06
     rozÅ¡ÃŃ
    0.06
     Stre
    0.06
     pilot
    0.06
     Address
    0.06
    imate
    0.06
     program
    0.06
     proof
    0.06
    Activations Density 0.028%

    No Known Activations