© 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. 15689
    Prev
    Next
    INDEX
    Explanations

    concepts related to leisure activities and their perceived benefits

    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
     Fucking
    -0.06
    (ed
    -0.06
    itom
    -0.06
     introdu
    -0.06
    ymm
    -0.06
    ô
    -0.06
    rem
    -0.06
    Ùģت
    -0.06
    _FN
    -0.06
    uthor
    -0.05
    POSITIVE LOGITS
     apparently
    0.08
     your
    0.07
    Apparently
    0.07
     TaÅŁ
    0.07
     science
    0.07
    Compile
    0.07
    your
    0.07
     According
    0.07
    ARGER
    0.07
    Science
    0.07
    Activations Density 0.023%

    No Known Activations