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

    Neuronpedia

    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. 127683
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to testing and error handling

    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
    jak
    -0.06
    ummies
    -0.06
    äºľ
    -0.06
    plural
    -0.06
    ssf
    -0.06
    ALAR
    -0.06
     unusually
    -0.05
    gression
    -0.05
     cl
    -0.05
    bor
    -0.05
    POSITIVE LOGITS
     expectations
    0.11
     comparison
    0.10
     expected
    0.10
     Comparison
    0.09
     Expected
    0.09
    .compare
    0.09
    Expected
    0.09
    Compare
    0.09
    comparison
    0.09
    expected
    0.09
    Activations Density 0.049%

    No Known Activations