© 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. 125202
    Prev
    Next
    INDEX
    Explanations

    discussions about homeschooling and early childhood education

    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
     Dorm
    -0.07
    otas
    -0.07
    awan
    -0.07
    oop
    -0.07
    Behaviour
    -0.07
    ogne
    -0.07
    DED
    -0.07
     REGION
    -0.07
    emale
    -0.06
    ayne
    -0.06
    POSITIVE LOGITS
     homeschool
    0.11
     Homes
    0.08
     home
    0.08
     alternative
    0.07
     Alternative
    0.07
    homes
    0.07
     Libert
    0.07
    èĩªçĶ±
    0.07
     homes
    0.06
     freedom
    0.06
    Activations Density 0.021%

    No Known Activations