© 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. 120807
    Prev
    Next
    INDEX
    Explanations

    coding elements related to object creation and relationships 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
    ysi
    -0.07
    erland
    -0.07
    ÌĨ
    -0.06
    coder
    -0.06
    zf
    -0.06
    pector
    -0.06
    ummer
    -0.06
     Leban
    -0.06
    utherland
    -0.06
    arah
    -0.06
    POSITIVE LOGITS
    aset
    0.07
    aginator
    0.07
    enso
    0.07
    .urls
    0.07
     Django
    0.06
     Garrison
    0.06
     Pred
    0.06
     Verb
    0.06
    ddie
    0.06
    oned
    0.06
    Activations Density 0.018%

    No Known Activations