© 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. 127457
    Prev
    Next
    INDEX
    Explanations

    instances where things are described as being covered, including various contexts and materials

    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
    одо
    -0.07
    ints
    -0.07
    imo
    -0.07
    enced
    -0.07
     chặt
    -0.07
    ovsky
    -0.07
    лоп
    -0.07
    رش
    -0.06
    sted
    -0.06
    oki
    -0.06
    POSITIVE LOGITS
     covering
    0.10
     coverage
    0.09
     layer
    0.08
    -cover
    0.08
    covering
    0.08
     covered
    0.08
    coverage
    0.08
     cover
    0.08
     COVER
    0.07
     blanket
    0.07
    Activations Density 0.013%

    No Known Activations