© 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. 15-LLAMASCOPE-RES-131K
    11. 90595
    Prev
    Next
    INDEX
    Explanations

    technical terms and keywords related to programming, specifically in Python and its libraries

    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
    ASA
    -0.06
    ag
    -0.06
    ůj
    -0.06
    %C
    -0.06
    illiseconds
    -0.06
     Regulatory
    -0.06
     dara
    -0.06
    ict
    -0.06
     Lyons
    -0.06
     regulatory
    -0.05
    POSITIVE LOGITS
    δÏħ
    0.07
    ıa
    0.07
     Ocak
    0.06
    ãĤ¤ãĤ¯
    0.06
     pathMatch
    0.06
     forKey
    0.06
    zyst
    0.06
    enco
    0.06
    Cooldown
    0.06
    olics
    0.06
    Activations Density 0.004%

    No Known Activations