© 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. 105203
    Prev
    Next
    INDEX
    Explanations

    phrases related to transactions and the exchange of money

    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
    ån
    -0.07
    uraa
    -0.07
    uplic
    -0.06
    dex
    -0.06
     Verfüg
    -0.06
    grades
    -0.06
    uent
    -0.06
    Ìĥ
    -0.06
    Æ°á»Ŀng
    -0.06
    eya
    -0.06
    POSITIVE LOGITS
     purchase
    0.18
     purchases
    0.16
     purchased
    0.16
    è´Ńä¹°
    0.14
     Purchase
    0.14
     bought
    0.14
    purchase
    0.14
     purchasing
    0.14
    Purchase
    0.13
     buying
    0.12
    Activations Density 0.099%

    No Known Activations