© 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. 78861
    Prev
    Next
    INDEX
    Explanations

    financial terms related to pension schemes and contributions

    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
    /Dk
    -0.07
    ulong
    -0.07
     fisse
    -0.07
    ADB
    -0.07
    awan
    -0.07
     strncmp
    -0.07
    _lua
    -0.07
    932
    -0.06
    Ø·ÙĦ
    -0.06
    onse
    -0.06
    POSITIVE LOGITS
     kr
    0.07
     Kr
    0.06
     permitted
    0.06
     xsi
    0.06
    夫
    0.06
    addAll
    0.06
     hel
    0.05
    osh
    0.05
     contribution
    0.05
     Wid
    0.05
    Activations Density 0.006%

    No Known Activations