© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 99135
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions and advisory services

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    rete
    -0.07
    vou
    -0.07
    nete
    -0.07
     trụ
    -0.07
    анк
    -0.07
     пл
    -0.07
    chg
    -0.07
     olab
    -0.07
    sov
    -0.07
    ikat
    -0.07
    POSITIVE LOGITS
    ACHED
    0.06
    upp
    0.06
     Sr
    0.06
    orus
    0.06
    ems
    0.06
    loud
    0.05
    abil
    0.05
    LOUD
    0.05
     Contact
    0.05
    auer
    0.05
    Activations Density 0.016%

    No Known Activations