© 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. 59910
    Prev
    Next
    INDEX
    Explanations

    phrases expressing strong emotional appeal or community engagement

    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
     thus
    -0.08
     latter
    -0.07
    uze
    -0.07
    rin
    -0.07
     både
    -0.07
    incinn
    -0.06
    аÑĤов
    -0.06
     notamment
    -0.06
     dÅĻÃŃ
    -0.06
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.06
    POSITIVE LOGITS
    æĹ¢çĦ¶
    0.07
    there
    0.06
     there
    0.06
    etin
    0.06
    keh
    0.06
    wil
    0.06
     sırada
    0.06
    stderr
    0.05
     unlike
    0.05
    ding
    0.05
    Activations Density 0.020%

    No Known Activations