© 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. 125686
    Prev
    Next
    INDEX
    Explanations

    references to web technologies and programming languages

    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
    oldem
    -0.08
    adera
    -0.08
    TestFixture
    -0.08
    asics
    -0.08
    ibri
    -0.07
     DÄĽ
    -0.07
    rosso
    -0.07
    /UIKit
    -0.07
    ãģ¾ãģļ
    -0.07
    é³´
    -0.07
    POSITIVE LOGITS
     alike
    0.06
     Uncategorized
    0.06
     development
    0.06
     unint
    0.06
     work
    0.06
    work
    0.05
    -int
    0.05
     filetype
    0.05
    081
    0.05
    thon
    0.05
    Activations Density 0.005%

    No Known Activations