© 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. 103431
    Prev
    Next
    INDEX
    Explanations

    file and code structure elements in programming

    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
    istrovstvÃŃ
    -0.06
     Contr
    -0.06
    ä¿®
    -0.06
    ey
    -0.06
    .IContainer
    -0.06
     recourse
    -0.06
    buster
    -0.05
     Dew
    -0.05
    StateException
    -0.05
     Flood
    -0.05
    POSITIVE LOGITS
    okes
    0.09
    idot
    0.08
    èĬĿ
    0.08
    ÄĽt
    0.07
    енÑĤи
    0.07
    aqu
    0.07
    uest
    0.07
    monic
    0.07
    太éĥİ
    0.07
    imeo
    0.07
    Activations Density 0.001%

    No Known Activations