© 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. 17073
    Prev
    Next
    INDEX
    Explanations

    coding-related terms and identifiers, particularly in programming documentation

    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
    334
    -0.06
    âĢ¦↵
    -0.06
     Gib
    -0.05
    732
    -0.05
    âĢ¦
    -0.05
     Estimates
    -0.05
     Geh
    -0.05
     [âĢ¦]↵
    -0.05
     tr
    -0.05
     Gad
    -0.05
    POSITIVE LOGITS
    imdi
    0.09
    ãģıãĤĮ
    0.08
     знов
    0.08
    Ñİк
    0.08
    Äįel
    0.08
    luv
    0.08
    //{{
    0.08
    ÅĻÃŃž
    0.08
    (.)
    0.08
    ICI
    0.08
    Activations Density 0.002%

    No Known Activations