© 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. 70536
    Prev
    Next
    INDEX
    Explanations

    references to financial struggles or challenges

    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
    veh
    -0.06
    tm
    -0.06
     Indies
    -0.06
     Cra
    -0.06
    endale
    -0.06
    acic
    -0.06
    302
    -0.05
    velt
    -0.05
    apos
    -0.05
    many
    -0.05
    POSITIVE LOGITS
     nackte
    0.08
    ̣
    0.07
    POINTS
    0.07
    IRQ
    0.07
     onDataChange
    0.07
     célib
    0.07
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.07
    BUF
    0.07
    ردÙĩ
    0.07
    evenodd
    0.07
    Activations Density 0.013%

    No Known Activations