© 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. 104976
    Prev
    Next
    INDEX
    Explanations

    references to education and societal values

    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
     ActionTypes
    -0.07
    itoris
    -0.07
    IfExists
    -0.06
    sr
    -0.06
     пÑĢоÑĤивоп
    -0.06
    Sr
    -0.06
    çľ
    -0.06
    iren
    -0.06
    neh
    -0.06
    åħ½
    -0.06
    POSITIVE LOGITS
     education
    0.13
     Education
    0.12
    education
    0.11
    æķĻèĤ²
    0.11
     Bild
    0.10
     children
    0.10
    Education
    0.10
     educational
    0.10
     teaching
    0.09
    ducation
    0.09
    Activations Density 0.180%

    No Known Activations