© 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. 74944
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to function definitions and assertions

    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
    irl
    -0.08
    iros
    -0.07
    ahi
    -0.07
    ephir
    -0.07
    ayah
    -0.07
    Tro
    -0.06
    estroy
    -0.06
    Ïģη
    -0.06
    usto
    -0.06
    ipment
    -0.06
    POSITIVE LOGITS
    .assertRaises
    0.09
    expectException
    0.08
     try
    0.08
     attempt
    0.08
    attempt
    0.08
    .Throws
    0.07
    ลà¸Ńà¸ĩ
    0.07
     Attempt
    0.07
     attempted
    0.07
    Attempt
    0.07
    Activations Density 0.010%

    No Known Activations