© 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. 73430
    Prev
    Next
    INDEX
    Explanations

    occurrences of social interactions involving various age groups and demographics

    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
    yas
    -0.08
    ulis
    -0.07
    ItemSelectedListener
    -0.07
     Jaune
    -0.07
    eree
    -0.07
    ersh
    -0.06
    (Font
    -0.06
    ìĤ´
    -0.06
    .closest
    -0.06
    á»Ĩ
    -0.06
    POSITIVE LOGITS
     elderly
    0.10
     age
    0.10
     young
    0.10
     ages
    0.09
     aged
    0.09
     sen
    0.08
     children
    0.07
     Young
    0.07
     adult
    0.07
     pension
    0.07
    Activations Density 0.134%

    No Known Activations