© 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. 4700
    Prev
    Next
    INDEX
    Explanations

    references to higher education and academic institutions

    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
    encil
    -0.06
    á»Ļng
    -0.06
    ola
    -0.06
     bi
    -0.05
    nds
    -0.05
    _ANT
    -0.05
     éĩ
    -0.05
    echa
    -0.05
    jin
    -0.05
    .hot
    -0.05
    POSITIVE LOGITS
    åĬŀ
    0.09
    964
    0.09
     institution
    0.08
    .Generated
    0.08
     Higher
    0.08
    -medium
    0.07
     Institution
    0.07
    higher
    0.07
    ystem
    0.07
     Teaching
    0.07
    Activations Density 0.080%

    No Known Activations