© 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. 17-LLAMASCOPE-RES-131K
    11. 85362
    Prev
    Next
    INDEX
    Explanations

    concepts related to early childhood education and parental involvement in literacy development

    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
    èįī
    -0.07
    cobra
    -0.07
    uppy
    -0.07
    toJson
    -0.06
    ald
    -0.06
    Teen
    -0.06
     Teen
    -0.06
    adolu
    -0.06
    ahu
    -0.06
    adol
    -0.06
    POSITIVE LOGITS
     stimulation
    0.08
     stimulus
    0.07
     stimuli
    0.07
     Ange
    0.07
     bonding
    0.06
    stim
    0.06
    ãĥ¼ãĥª
    0.06
     prest
    0.06
     Prest
    0.06
     language
    0.06
    Activations Density 0.008%

    No Known Activations