© 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. 60153
    Prev
    Next
    INDEX
    Explanations

    occurrences of class inheritance in programming-related texts

    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
    HT
    -0.06
    .arm
    -0.06
    æīķ
    -0.06
    -modules
    -0.06
     stab
    -0.05
     tant
    -0.05
    ربÙĬØ©
    -0.05
     ser
    -0.05
    é¢
    -0.05
     bindings
    -0.05
    POSITIVE LOGITS
    vre
    0.09
     Abstract
    0.09
     abstract
    0.09
    öz
    0.07
    Abstract
    0.07
    .Abstract
    0.07
    plies
    0.07
    azel
    0.07
    åŁº
    0.07
    (DBG
    0.07
    Activations Density 0.003%

    No Known Activations