© 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. 82149
    Prev
    Next
    INDEX
    Explanations

    terms related to formal documentation and structured content in various domains

    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
    -0.06
    cop
    -0.06
     screens
    -0.06
     bells
    -0.06
     profile
    -0.05
     Balk
    -0.05
    arker
    -0.05
    ÑĪла
    -0.05
    datagrid
    -0.05
    Enum
    -0.05
    POSITIVE LOGITS
    stable
    0.08
    -collection
    0.08
     collection
    0.07
    Ïīν
    0.07
    .nano
    0.07
    ographs
    0.07
    -fontawesome
    0.07
    OfType
    0.07
    767
    0.07
    stroy
    0.07
    Activations Density 0.039%

    No Known Activations