© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 30129
    Prev
    Next
    INDEX
    Explanations

    phrases related to education and data science

    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
    arend
    -0.09
    aversal
    -0.08
    ynchronization
    -0.08
    lep
    -0.08
    ạp
    -0.08
    dle
    -0.08
    apolis
    -0.07
    ÑĢаÑĩ
    -0.07
    stanov
    -0.07
    eled
    -0.07
    POSITIVE LOGITS
     Kag
    0.10
     Data
    0.07
     data
    0.07
     Machine
    0.07
    /data
    0.06
     Analyst
    0.06
     analyst
    0.06
    eto
    0.06
     projects
    0.06
     training
    0.06
    Activations Density 0.042%

    No Known Activations