© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 30616
    Prev
    Next
    INDEX
    Explanations

    elements related to sports and performance

    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
     retired
    -0.13
     retire
    -0.11
     elderly
    -0.11
     retirees
    -0.10
     retirement
    -0.10
    elder
    -0.09
     professor
    -0.09
     retiring
    -0.09
    Professor
    -0.09
     veteran
    -0.09
    POSITIVE LOGITS
     young
    0.12
    young
    0.10
     jeune
    0.10
     genç
    0.08
     student
    0.08
     Young
    0.08
    éĿĴå¹´
    0.08
     joven
    0.07
     लड
    0.07
     Student
    0.07
    Activations Density 0.198%

    No Known Activations