© 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. 55498
    Prev
    Next
    INDEX
    Explanations

    references to organized event logistics and structures akin to a "bubble" environment

    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
    uyo
    -0.07
    ickers
    -0.06
    INTR
    -0.06
    æĺĩ
    -0.06
    UF
    -0.06
    Corner
    -0.06
     LIC
    -0.06
    summ
    -0.06
     Cornell
    -0.06
    angs
    -0.06
    POSITIVE LOGITS
     isolation
    0.09
     Bubble
    0.09
     bubble
    0.09
     hotel
    0.08
    åijĨ
    0.07
    Bubble
    0.07
     isolate
    0.07
    bubble
    0.07
    hotel
    0.07
     isol
    0.07
    Activations Density 0.004%

    No Known Activations