© 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. 15882
    Prev
    Next
    INDEX
    Explanations

    key terms and details related to financial reporting and metrics

    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
    æĮ¯
    -0.08
    aille
    -0.07
    ails
    -0.06
    avier
    -0.06
    illes
    -0.06
     Circuit
    -0.06
    lok
    -0.06
    ики
    -0.06
    arily
    -0.05
    ائÙĤ
    -0.05
    POSITIVE LOGITS
    ลาà¸Ķ
    0.07
    عب
    0.06
    Hint
    0.06
    ека
    0.06
    .Yes
    0.06
    emiz
    0.06
    âĹİ
    0.06
    CHAN
    0.06
    ë§Ŀ
    0.06
     yem
    0.06
    Activations Density 0.001%

    No Known Activations