© 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. 41931
    Prev
    Next
    INDEX
    Explanations

    discussions related to benchmarking and data evaluation

    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
    ozy
    -0.06
    MUX
    -0.06
    ož
    -0.06
    vala
    -0.06
    boxed
    -0.06
     dün
    -0.06
    Newton
    -0.06
    สล
    -0.06
    ráž
    -0.06
    loff
    -0.06
    POSITIVE LOGITS
     benchmark
    0.10
     Benchmark
    0.09
     benchmarks
    0.08
     Bench
    0.08
     peer
    0.08
     comparison
    0.08
     compare
    0.08
    Benchmark
    0.08
    benchmark
    0.08
     comparative
    0.07
    Activations Density 0.008%

    No Known Activations