© 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. 15425
    Prev
    Next
    INDEX
    Explanations

    terms related to code generation and programming constructs

    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
     wool
    -0.06
    kek
    -0.06
    arness
    -0.05
    ãĤĨ
    -0.05
    assen
    -0.05
    ój
    -0.05
    kest
    -0.05
    entine
    -0.05
    ilon
    -0.05
    awi
    -0.05
    POSITIVE LOGITS
    hub
    0.07
     Verfüg
    0.07
     automát
    0.07
    ाध
    0.07
     èĩªåĬ¨çĶŁæĪIJ
    0.07
    lsa
    0.07
    ADF
    0.07
     رضا
    0.07
    λεÏį
    0.07
    аков
    0.07
    Activations Density 0.001%

    No Known Activations