© 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. 57745
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to error-checking and debugging features

    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
    ench
    -0.08
    auga
    -0.07
    à¸ļาย
    -0.07
    affer
    -0.06
    AGON
    -0.06
    illard
    -0.06
     Dock
    -0.06
     Ow
    -0.06
    indow
    -0.06
    ories
    -0.06
    POSITIVE LOGITS
    printStats
    0.07
    #error
    0.06
    .annotations
    0.06
    quare
    0.06
    .onViewCreated
    0.06
     nominal
    0.06
     TMPro
    0.06
     Constructors
    0.06
    ká
    0.06
     prelim
    0.06
    Activations Density 0.045%

    No Known Activations