© 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. 86673
    Prev
    Next
    INDEX
    Explanations

    references to financial status and net worth

    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
    .Dto
    -0.08
    æk
    -0.07
    ramid
    -0.07
    igor
    -0.07
    .docs
    -0.06
    agra
    -0.06
     leakage
    -0.06
    aroo
    -0.06
    igans
    -0.06
    rek
    -0.06
    POSITIVE LOGITS
    timeofday
    0.07
     Trot
    0.07
    ajas
    0.07
    AutoSize
    0.06
     Ble
    0.06
     estimated
    0.06
    iah
    0.06
     Shepherd
    0.06
    ãģ¡ãģ¯
    0.06
    _gettime
    0.06
    Activations Density 0.001%

    No Known Activations