© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 75582
    Prev
    Next
    INDEX
    Explanations

    references to reflection or security 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
    eniz
    -0.09
    ertz
    -0.09
    ogan
    -0.09
    ä¿Ĭ
    -0.07
    lean
    -0.07
    vue
    -0.07
    cul
    -0.07
    culus
    -0.07
    igital
    -0.07
    arih
    -0.06
    POSITIVE LOGITS
    egov
    0.06
    ÙĤد
    0.06
    ting
    0.06
    s
    0.06
     glor
    0.06
    CEPTION
    0.06
    rames
    0.05
     sacr
    0.05
    airs
    0.05
    IMIZE
    0.05
    Activations Density 0.000%

    No Known Activations