© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 128507
    Prev
    Next
    INDEX
    Explanations

    phrases related to investment performance and comparisons

    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
    irth
    -0.08
    anik
    -0.08
    714
    -0.07
    -fontawesome
    -0.07
     çł
    -0.06
    .ec
    -0.06
    κά
    -0.06
    abad
    -0.06
    orc
    -0.06
    PTY
    -0.06
    POSITIVE LOGITS
     peers
    0.08
     benchmarks
    0.08
     industry
    0.07
    Benchmark
    0.07
     Benchmark
    0.07
     benchmark
    0.07
    aph
    0.07
     alternatives
    0.06
     average
    0.06
     mainstream
    0.06
    Activations Density 0.007%

    No Known Activations