© 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. 88319
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and concepts, particularly those associated with query handling and method usage

    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
    	TokenName
    -0.07
     nargin
    -0.07
    OCUS
    -0.07
    ortic
    -0.06
    ç´ł
    -0.06
    GLOBALS
    -0.06
    moduleId
    -0.06
    assi
    -0.06
    Alan
    -0.06
     createState
    -0.06
    POSITIVE LOGITS
     filter
    0.07
    ToList
    0.07
    itez
    0.07
     lazy
    0.07
     Tail
    0.06
    icari
    0.06
     stream
    0.06
     deferred
    0.06
    GetInt
    0.06
     ret
    0.06
    Activations Density 0.021%

    No Known Activations