© 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 EvalsExportsinterp-engineNEWAPI 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. 120707
    Prev
    Next
    INDEX
    Explanations

    terminologies related to neural network architectures and their mathematical representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Author names and publication years within LaTeX citation commands (\cite{}) in academic/scientific papers.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     integ
    -0.08
    /Foundation
    -0.07
    ạp
    -0.07
    ugin
    -0.07
    borg
    -0.06
    imetype
    -0.06
    ollo
    -0.06
    eah
    -0.06
    unami
    -0.06
     neust
    -0.06
    POSITIVE LOGITS
     training
    0.09
     Neural
    0.08
     neural
    0.08
     learning
    0.08
    GAN
    0.07
    /train
    0.07
     Lear
    0.07
     trained
    0.07
    .learn
    0.07
    learn
    0.07
    Activations Density 0.302%

    No Known Activations