© 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. 127320
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial expenses and their consequences

    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
    延
    -0.07
    acon
    -0.06
    anine
    -0.06
    usal
    -0.06
    OrNil
    -0.06
    alus
    -0.06
    ÄĽk
    -0.06
    arResult
    -0.06
    addtogroup
    -0.06
    888
    -0.06
    POSITIVE LOGITS
     quickly
    0.20
     rapid
    0.18
    rapid
    0.17
     rapidly
    0.17
    quick
    0.16
     Rapid
    0.15
     quick
    0.15
     QUICK
    0.14
     rápido
    0.14
    .quick
    0.14
    Activations Density 0.064%

    No Known Activations