© 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. 87407
    Prev
    Next
    INDEX
    Explanations

    references to children's educational programs

    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
    chartInstance
    -0.07
    wdx
    -0.07
    поÑĢ
    -0.07
    erton
    -0.06
    ãĥ¼ãĥĵ
    -0.06
    aldi
    -0.06
    驱
    -0.06
    enson
    -0.06
    endif
    -0.06
    agara
    -0.06
    POSITIVE LOGITS
    ãģķãģ¾
    0.07
    Ïģκ
    0.06
     Babies
    0.06
    Benchmark
    0.06
     Transitional
    0.06
    rog
    0.06
    -metadata
    0.06
     Floyd
    0.06
    esco
    0.06
    ãĤ¶ãĥ¼
    0.06
    Activations Density 0.001%

    No Known Activations