© 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. 118802
    Prev
    Next
    INDEX
    Explanations

    themes related to educational programs and opportunities for personal growth and 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
    izzer
    -0.07
    ateg
    -0.07
    ailer
    -0.07
     پاÛĮ
    -0.07
    iyan
    -0.07
    enaire
    -0.06
    oris
    -0.06
    _TCP
    -0.06
    .EventHandler
    -0.06
    izin
    -0.06
    POSITIVE LOGITS
     each
    0.10
     individuals
    0.09
     individual
    0.08
     these
    0.08
     participants
    0.07
    each
    0.07
    comed
    0.07
    individual
    0.07
     candidates
    0.06
     students
    0.06
    Activations Density 0.039%

    No Known Activations