© 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. 86966
    Prev
    Next
    INDEX
    Explanations

    directives related to maintaining simplicity and naturalness in various contexts

    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
    iphy
    -0.06
    verse
    -0.06
    ade
    -0.06
     Bid
    -0.06
     Cole
    -0.06
     besten
    -0.06
    periences
    -0.06
     Dag
    -0.05
     Dil
    -0.05
     DBG
    -0.05
    POSITIVE LOGITS
    Multiplicity
    0.08
     simplicity
    0.08
    _Execute
    0.08
     SIMPLE
    0.08
    -simple
    0.08
    DUCT
    0.08
    chio
    0.07
    ToOne
    0.07
    simple
    0.07
    ductive
    0.07
    Activations Density 0.014%

    No Known Activations