© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 85057
    Prev
    Next
    INDEX
    Explanations

    educational programs and degrees related to various fields of study

    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
     undergraduate
    -0.08
    tester
    -0.08
     undergrad
    -0.08
    asd
    -0.08
    andest
    -0.07
    ardy
    -0.07
     Atkins
    -0.07
    ativ
    -0.06
    ordial
    -0.06
     Cobra
    -0.06
    POSITIVE LOGITS
    .addField
    0.07
     program
    0.07
    rie
    0.07
     cum
    0.07
    chten
    0.06
     degree
    0.06
    -degree
    0.06
    plode
    0.06
    InputChange
    0.06
    822
    0.06
    Activations Density 0.024%

    No Known Activations