© 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. 41956
    Prev
    Next
    INDEX
    Explanations

    concepts related to childhood care and education interventions

    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
    locker
    -0.08
    edImage
    -0.08
    .scalablytyped
    -0.07
    SearchTree
    -0.07
    Pie
    -0.07
    ahu
    -0.07
     ÙĤØ·
    -0.07
    stva
    -0.07
     '".$_
    -0.07
     slice
    -0.06
    POSITIVE LOGITS
     Development
    0.07
     Program
    0.07
     Household
    0.07
     household
    0.06
    æĩ
    0.06
     dop
    0.06
    odeled
    0.06
     Early
    0.06
     Healthy
    0.05
     Resource
    0.05
    Activations Density 0.005%

    No Known Activations