© 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. 22-LLAMASCOPE-RES-131K
    11. 3640
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and software development concepts, particularly rules, middleware, and macros

    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
     sick
    -0.06
     cheap
    -0.06
    oe
    -0.06
    uchen
    -0.06
    igin
    -0.05
    agn
    -0.05
    à¸Ńà¸Ń
    -0.05
     accessor
    -0.05
     Cheap
    -0.05
    Cheap
    -0.05
    POSITIVE LOGITS
     definitions
    0.10
     definition
    0.10
    definition
    0.09
    Definition
    0.09
    definitions
    0.09
    -definition
    0.08
     Definition
    0.08
     Definitions
    0.08
    åIJį称
    0.08
    âĢ¦↵↵↵
    0.07
    Activations Density 0.080%

    No Known Activations