© 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. 60387
    Prev
    Next
    INDEX
    Explanations

    references to software development and package management systems

    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
     Cole
    -0.07
     dec
    -0.07
     Dining
    -0.06
    usable
    -0.05
    ķĮ
    -0.05
    驱
    -0.05
    reading
    -0.05
     Composite
    -0.05
    Cole
    -0.05
    Reading
    -0.05
    POSITIVE LOGITS
     release
    0.09
    orelease
    0.09
     Release
    0.09
    -release
    0.09
     distribution
    0.08
    release
    0.08
     Distribution
    0.08
     çĻ¼
    0.08
    μαÏĦο
    0.08
     releasing
    0.07
    Activations Density 0.010%

    No Known Activations