© 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. 5-LLAMASCOPE-RES-131K
    11. 126762
    Prev
    Next
    INDEX
    Explanations

    programming and coding-related constructs and operations.

    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
    ãĤĪ
    -0.06
    orget
    -0.06
    дÑĢ
    -0.06
     fee
    -0.06
    antage
    -0.06
    utm
    -0.06
    krit
    -0.06
    uve
    -0.05
     Wealth
    -0.05
    gem
    -0.05
    POSITIVE LOGITS
    خاÙĨÙĩ
    0.07
    bard
    0.07
    _super
    0.07
    igans
    0.06
    -addon
    0.06
    å¹¹ç·ļ
    0.06
     Casc
    0.06
    ossa
    0.06
    rossover
    0.06
    oly
    0.06
    Activations Density 0.001%

    No Known Activations