© 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. 86949
    Prev
    Next
    INDEX
    Explanations

    terms related to operating 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
    Chicago
    -0.10
     Chicago
    -0.10
     chicago
    -0.09
    .scalablytyped
    -0.09
    regnum
    -0.08
    locker
    -0.08
     addCriterion
    -0.08
    uib
    -0.08
    Locker
    -0.08
    ustil
    -0.08
    POSITIVE LOGITS
     Delaware
    0.15
     Wilmington
    0.13
     Sussex
    0.11
    ilmington
    0.09
     Dover
    0.08
     Dresden
    0.08
     Newark
    0.08
     Brighton
    0.08
     FreeBSD
    0.08
     Surrey
    0.07
    Activations Density 0.102%

    No Known Activations