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. 44189
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols in 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
     Shapiro
    -0.07
     Harlem
    -0.07
     SA
    -0.07
     Jews
    -0.07
     IA
    -0.06
     Hawth
    -0.06
     Hispanics
    -0.06
     JA
    -0.06
     HA
    -0.06
     Juda
    -0.06
    POSITIVE LOGITS
     Deniz
    0.19
     Turkey
    0.17
     Turkish
    0.17
     Erg
    0.17
     ErdoÄŁan
    0.16
    Turkey
    0.16
     Erdogan
    0.16
     Ankara
    0.15
     turkey
    0.14
     Atatürk
    0.14
    Activations Density 0.002%

    No Known Activations