© 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 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. 3660
    Prev
    Next
    INDEX
    Explanations

    references to financial transactions and payments

    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
    ello
    -0.09
    Builders
    -0.08
    assin
    -0.08
    /trunk
    -0.08
    anders
    -0.07
    *)_
    -0.07
    _Anim
    -0.07
    åģ·
    -0.07
     pregn
    -0.07
     createStore
    -0.07
    POSITIVE LOGITS
    ,
    0.06
     employees
    0.06
     directly
    0.06
     Coalition
    0.06
     lawyers
    0.06
     individuals
    0.05
    287
    0.05
     lic
    0.05
    952
    0.05
     licensed
    0.05
    Activations Density 0.020%

    No Known Activations