© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 55369
    Prev
    Next
    INDEX
    Explanations

    descriptions of performance and comfort attributes in products

    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
    olis
    -0.08
    ôm
    -0.07
    .fp
    -0.06
    身
    -0.06
    ленно
    -0.06
    DELAY
    -0.06
    ÏĢή
    -0.06
    accessible
    -0.06
    adelphia
    -0.06
    lot
    -0.06
    POSITIVE LOGITS
     when
    0.10
     during
    0.09
    _when
    0.09
    when
    0.09
    	when
    0.09
     whenever
    0.08
     cuando
    0.07
     WHEN
    0.07
    during
    0.07
     under
    0.07
    Activations Density 0.059%

    No Known Activations