© 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. 40447
    Prev
    Next
    INDEX
    Explanations

    method and function definitions in programming code

    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
     Goodman
    -0.07
     pij
    -0.06
    ([&
    -0.06
     return
    -0.06
     Todd
    -0.06
     Outer
    -0.06
    (return
    -0.06
     massaggi
    -0.06
    gne
    -0.06
     Annotation
    -0.05
    POSITIVE LOGITS
     InitializeComponent
    0.09
    initWith
    0.08
    _ctor
    0.07
    _initialize
    0.07
     parent
    0.07
    _init
    0.07
     super
    0.07
    볨
    0.07
     init
    0.07
    .initialize
    0.07
    Activations Density 0.044%

    No Known Activations