© 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. 9-LLAMASCOPE-RES-131K
    11. 95816
    Prev
    Next
    INDEX
    Explanations

    names and titles of political figures

    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
    égor
    -0.07
     voks
    -0.06
    主任
    -0.06
    igel
    -0.06
     ЧаÑģ
    -0.06
    _rewrite
    -0.06
    ktop
    -0.06
    dee
    -0.06
    jun
    -0.06
    æ¡Ī
    -0.06
    POSITIVE LOGITS
    vik
    0.07
    UnitOfWork
    0.07
    noinspection
    0.06
     deter
    0.06
    bones
    0.06
    ÏĨι
    0.06
     GHC
    0.06
     enc
    0.06
    ,exports
    0.06
    Enc
    0.06
    Activations Density 0.023%

    No Known Activations