© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77946
    Prev
    Next
    INDEX
    Explanations

    elements related to social gatherings and celebrations

    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
    okud
    -0.09
    iku
    -0.07
    decltype
    -0.07
    Children
    -0.06
    -pagination
    -0.06
    оÑİ
    -0.06
     sey
    -0.06
    تاب
    -0.06
    æ¨Ĥ
    -0.06
    .setPrototypeOf
    -0.06
    POSITIVE LOGITS
     party
    0.08
     Party
    0.08
    bond
    0.08
    ³
    0.07
     GROUP
    0.07
    awk
    0.06
     bond
    0.06
    zi
    0.06
    party
    0.06
     Bond
    0.06
    Activations Density 0.004%

    No Known Activations