© 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. 54543
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to namespaces, modules, and classes in code

    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
    ville
    -0.06
    ilor
    -0.06
    Æ¡
    -0.06
    ãĢģç§ģ
    -0.06
    ová
    -0.06
     tá»
    -0.06
     Advances
    -0.06
    ÛĮÙĩ
    -0.06
    macros
    -0.05
    Dimension
    -0.05
    POSITIVE LOGITS
     xlink
    0.08
    038
    0.07
    argout
    0.07
    vero
    0.06
    istrovstvÃŃ
    0.06
    adÃŃ
    0.06
     eskort
    0.06
    lemetry
    0.06
    weetalert
    0.06
    EDA
    0.06
    Activations Density 0.003%

    No Known Activations