© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 126539
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals and social media handles

    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
    593
    -0.06
    itech
    -0.06
    esion
    -0.06
    enburg
    -0.06
     assignment
    -0.06
    893
    -0.06
    assing
    -0.05
    iators
    -0.05
     works
    -0.05
     synthetic
    -0.05
    POSITIVE LOGITS
    ityEngine
    0.09
    Official
    0.08
     Official
    0.08
    fans
    0.07
    .btnClose
    0.07
    gue
    0.07
    official
    0.07
     ÙĪÙĦد
    0.07
    _actor
    0.07
    .XPath
    0.07
    Activations Density 0.009%

    No Known Activations