© 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. 105338
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial processes and obligations

    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
    ninger
    -0.06
    zano
    -0.06
    ester
    -0.06
     tac
    -0.06
     Fav
    -0.06
    apot
    -0.06
    orsi
    -0.06
    iesel
    -0.06
     sp
    -0.06
    ieux
    -0.05
    POSITIVE LOGITS
     nackte
    0.08
    mÃŃt
    0.07
     lesbi
    0.07
     addCriterion
    0.07
    iani
    0.07
    ázd
    0.07
    ovice
    0.07
    eview
    0.07
    CLUD
    0.07
     καν
    0.06
    Activations Density 0.011%

    No Known Activations