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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 103947
    Prev
    Next
    INDEX
    Explanations

    information related to marriage requirements and ceremonies

    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
    éŀ
    -0.08
     æĬķ稿
    -0.07
    ekler
    -0.07
    estone
    -0.07
     dök
    -0.07
    udades
    -0.07
    /fw
    -0.07
    ÏĥÏĩ
    -0.07
    okus
    -0.07
    Ñıг
    -0.07
    POSITIVE LOGITS
     canonical
    0.07
     Gund
    0.06
    ibly
    0.06
     Rog
    0.06
     offic
    0.06
     Lawn
    0.06
     Rug
    0.06
     dispens
    0.05
     RC
    0.05
     incur
    0.05
    Activations Density 0.105%

    No Known Activations