© 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. 30977
    Prev
    Next
    INDEX
    Explanations

    references to historical or noble lineage, particularly pertaining to family backgrounds

    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
    bak
    -0.08
    ì´Į
    -0.07
    aign
    -0.07
    uty
    -0.07
    avad
    -0.07
    ák
    -0.07
    tere
    -0.06
    aren
    -0.06
    arena
    -0.06
     arenas
    -0.06
    POSITIVE LOGITS
     families
    0.18
     Families
    0.15
    amilies
    0.13
     households
    0.09
     famil
    0.09
    家æĹı
    0.09
     clans
    0.09
     fam
    0.08
     family
    0.08
     dynasty
    0.08
    Activations Density 0.059%

    No Known Activations