© 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. 69670
    Prev
    Next
    INDEX
    Explanations

    legislative discussions and agreements

    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
    tring
    -0.07
     tụ
    -0.06
    Clipboard
    -0.06
    eras
    -0.06
    LocalizedString
    -0.06
    ÏĥοÏħ
    -0.06
     cÃłng
    -0.06
     boldly
    -0.06
    컬
    -0.06
    رش
    -0.06
    POSITIVE LOGITS
     agreement
    0.14
     agreed
    0.10
    agree
    0.10
     Agreement
    0.10
     agreeing
    0.09
     agree
    0.09
     agreements
    0.09
     AGRE
    0.08
    ç»Īäºİ
    0.08
     final
    0.07
    Activations Density 0.027%

    No Known Activations