© 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. 92865
    Prev
    Next
    INDEX
    Explanations

    code-related terms and XML elements

    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
    onto
    -0.07
    ResultsController
    -0.06
    isay
    -0.06
    å¹»
    -0.06
    juven
    -0.06
    asso
    -0.06
     Bard
    -0.06
    ombat
    -0.06
    CCCCCC
    -0.06
    stice
    -0.06
    POSITIVE LOGITS
     XML
    0.11
    .xml
    0.11
     xml
    0.11
    xml
    0.10
    _xml
    0.10
    CDATA
    0.10
    XML
    0.10
    .XML
    0.10
     Xml
    0.09
     xmlns
    0.09
    Activations Density 0.100%

    No Known Activations