© 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. 15-LLAMASCOPE-RES-131K
    11. 103138
    Prev
    Next
    INDEX
    Explanations

    themes of time and routine in daily life

    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
     Stra
    -0.07
    ses
    -0.07
     Jug
    -0.06
     jan
    -0.06
     rec
    -0.06
     overlooked
    -0.05
     Zwe
    -0.05
     Athe
    -0.05
    otti
    -0.05
     sing
    -0.05
    POSITIVE LOGITS
    Insets
    0.08
     ngủ
    0.07
    ffset
    0.07
    rowse
    0.07
     hÆ°á»Łng
    0.07
    stanov
    0.07
     UIApplication
    0.07
    TestClass
    0.07
    USTER
    0.07
    _sleep
    0.07
    Activations Density 0.004%

    No Known Activations