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. 43708
    Prev
    Next
    INDEX
    Explanations

    proper names of characters and actors in movies

    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
    aders
    -0.06
    úÄįast
    -0.06
    venta
    -0.06
     åıĬ
    -0.06
    _DISABLE
    -0.06
     ÑĤоÑīо
    -0.06
    ergisi
    -0.06
    \Resources
    -0.06
    printer
    -0.06
    ï¼ĭ
    -0.06
    POSITIVE LOGITS
     repr
    0.10
    饰
    0.09
     sporting
    0.09
     playing
    0.09
    飾
    0.08
     plays
    0.08
     portraying
    0.08
     channel
    0.08
    playing
    0.08
     channels
    0.08
    Activations Density 0.008%

    No Known Activations