© 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 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. 9-LLAMASCOPE-RES-131K
    11. 96686
    Prev
    Next
    INDEX
    Explanations

    references to parenting and child-rearing experiences

    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
     Gre
    -0.07
    ungan
    -0.06
    еÑĤÑĥ
    -0.06
    Į¨
    -0.06
    zung
    -0.06
    åIJIJ
    -0.06
     EntityState
    -0.06
    .nc
    -0.06
    inz
    -0.06
    urgery
    -0.06
    POSITIVE LOGITS
     swell
    0.07
    531
    0.06
     Kelley
    0.06
     Notices
    0.05
    enever
    0.05
     Sikh
    0.05
    _rwlock
    0.05
    çĴ°
    0.05
     Kraft
    0.05
    ibold
    0.05
    Activations Density 0.025%

    No Known Activations