© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 123461
    Prev
    Next
    INDEX
    Explanations

    elements and structures related to the Document Object Model (DOM) in programming contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ome
    -0.08
    omnia
    -0.07
    ño
    -0.07
    iform
    -0.07
    esModule
    -0.07
     Demp
    -0.07
    eenth
    -0.07
    ably
    -0.07
    hod
    -0.07
    ux
    -0.07
    POSITIVE LOGITS
    s
    0.09
    357
    0.06
     AIDS
    0.06
    .snap
    0.06
    anza
    0.06
    ULAR
    0.06
     Shir
    0.06
    ference
    0.06
    BJECT
    0.06
    Ùĩ
    0.06
    Activations Density 0.004%

    No Known Activations