Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44038
    Prev
    Next
    INDEX
    Explanations

    special characters and non-English words in the document

    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
    1
    -0.07
    3
    -0.07
    2
    -0.07
     Hampshire
    -0.06
    8
    -0.06
    4
    -0.06
     colored
    -0.06
    9
    -0.06
    6
    -0.06
    5
    -0.05
    POSITIVE LOGITS
     Türk
    0.19
     Tür
    0.18
     Turkish
    0.17
     Turkey
    0.16
     Turks
    0.16
     Ãĸ
    0.15
     Türkiye
    0.15
     Atatürk
    0.15
    Türk
    0.15
    Turkey
    0.15
    Activations Density 0.001%

    No Known Activations