© 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. 119158
    Prev
    Next
    INDEX
    Explanations

    references to birth and citizenship issues

    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
    rop
    -0.07
    wil
    -0.06
    pur
    -0.06
     Partner
    -0.06
     Bak
    -0.06
    ous
    -0.06
    ÑĮÑİ
    -0.06
     dy
    -0.06
     Nova
    -0.06
     CreateMap
    -0.06
    POSITIVE LOGITS
     birth
    0.10
     Birth
    0.09
    Birth
    0.08
    birth
    0.08
     born
    0.08
     ÑĢождениÑı
    0.08
     births
    0.07
    \Migrations
    0.07
     nÄĥ
    0.07
    ERIC
    0.07
    Activations Density 0.003%

    No Known Activations