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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 94479
    Prev
    Next
    INDEX
    Explanations

    references to family interactions and relationships

    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
    gent
    -0.07
    ä¸Ī夫
    -0.07
    bai
    -0.07
     gent
    -0.06
    istani
    -0.06
    beh
    -0.06
    ellas
    -0.06
    anon
    -0.06
    elles
    -0.06
    chod
    -0.06
    POSITIVE LOGITS
     visit
    0.11
     visits
    0.10
     visiting
    0.09
    visit
    0.08
     weekend
    0.08
     visite
    0.08
     visita
    0.08
     weekends
    0.08
     visitors
    0.07
     Vis
    0.07
    Activations Density 0.027%

    No Known Activations