© 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. 41941
    Prev
    Next
    INDEX
    Explanations

    references to youth development and educational support programs

    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
    alez
    -0.08
    UrlParser
    -0.08
    ouri
    -0.08
    ÃŁe
    -0.08
    .Xaml
    -0.08
    isin
    -0.07
    ekl
    -0.07
    imd
    -0.07
    Highlights
    -0.07
    CppClass
    -0.07
    POSITIVE LOGITS
     neutral
    0.06
     Woodward
    0.06
     nucleus
    0.06
     Shay
    0.06
    (s
    0.06
     se
    0.06
     Grant
    0.06
    444
    0.06
     support
    0.06
    ero
    0.06
    Activations Density 0.041%

    No Known Activations