© 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. 17-LLAMASCOPE-RES-131K
    11. 93549
    Prev
    Next
    INDEX
    Explanations

    specific dates and numbers within the text

    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
    endet
    -0.06
    lem
    -0.06
    asset
    -0.06
    spacer
    -0.06
     buz
    -0.05
    ↵
    -0.05
     naive
    -0.05
    gili
    -0.05
    ORA
    -0.05
     Julien
    -0.05
    POSITIVE LOGITS
    ÙĪÛĮس
    0.07
    uggy
    0.07
    ãĥªãĤ¢
    0.07
    -alist
    0.07
    ÐľÐŀ
    0.07
     Bylo
    0.07
    Ø´ÙĪ
    0.07
    大åħ¨
    0.07
    _ter
    0.07
     ÙħÙĪب
    0.07
    Activations Density 0.003%

    No Known Activations