© 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 EvalsExportsinterp-engineNEWAPI 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. 104860
    Prev
    Next
    INDEX
    Explanations

    references to testing protocols and performance metrics

    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
     country
    -0.07
     casting
    -0.07
    erman
    -0.07
    enco
    -0.06
     Ey
    -0.06
    檢
    -0.06
    ermann
    -0.06
     Reviews
    -0.06
     Shan
    -0.06
     Cast
    -0.05
    POSITIVE LOGITS
     benchmark
    0.12
    Benchmark
    0.12
     Benchmark
    0.11
    benchmark
    0.11
    bench
    0.10
     bench
    0.10
     benchmarks
    0.10
     Bench
    0.10
     benches
    0.10
     run
    0.09
    Activations Density 0.048%

    No Known Activations