© 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. 95787
    Prev
    Next
    INDEX
    Explanations

    terms related to banking and finance

    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
    eras
    -0.06
    eral
    -0.06
     pronunciation
    -0.06
     paid
    -0.06
     bought
    -0.06
     Zub
    -0.05
    _
    -0.05
     groove
    -0.05
     Career
    -0.05
     bargain
    -0.05
    POSITIVE LOGITS
     APR
    0.08
     UIG
    0.07
    nesc
    0.07
    вÑĸлÑĮ
    0.07
    dna
    0.07
    pong
    0.07
    kı
    0.07
    poÄįet
    0.07
    ÙijÙĩ
    0.07
    .AppSettings
    0.07
    Activations Density 0.000%

    No Known Activations