© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 106299
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and structures, particularly focusing on data parsing and object management

    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
    inz
    -0.06
     lik
    -0.06
    crest
    -0.06
    .CreateInstance
    -0.06
    :\/\/
    -0.05
    coni
    -0.05
    ê¶ģ
    -0.05
     inher
    -0.05
    hape
    -0.05
     remains
    -0.05
    POSITIVE LOGITS
    ãĢįãģ®
    0.10
    ãĢĭçļĦ
    0.09
    odore
    0.08
    edom
    0.08
    "]->
    0.08
     addCriterion
    0.08
    >()->
    0.08
    ãĢįçļĦ
    0.07
    )ìĿĺ
    0.07
    ')['
    0.07
    Activations Density 0.193%

    No Known Activations