© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 55165
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or individuals, particularly in contexts related to businesses, politics, or public 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
     certainly
    -0.07
    ãģµ
    -0.07
    _binding
    -0.07
     definitely
    -0.07
    ouser
    -0.06
    zin
    -0.06
    chrome
    -0.06
    aley
    -0.06
    ãĤ¹ãĥŀ
    -0.06
     Certainly
    -0.06
    POSITIVE LOGITS
    ç«Ł
    0.09
     بتÙĪاÙĨ
    0.08
    å¦ĤæѤ
    0.07
    ãģĿãģĨãģª
    0.07
     à¤ĩतन
    0.07
     tão
    0.07
    è¿Ļä¹Ī
    0.06
    ÅĽnie
    0.06
    ãģĵãĤĵãģª
    0.06
     seemingly
    0.06
    Activations Density 0.030%

    No Known Activations