© 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. 17-LLAMASCOPE-RES-131K
    11. 42805
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial misconduct or mis-selling

    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
    à¥ģà¤Ł
    -0.09
    æ¬ł
    -0.07
    lector
    -0.07
    -wage
    -0.07
    Subsystem
    -0.07
    /course
    -0.07
    aea
    -0.07
    @brief
    -0.07
    ouri
    -0.07
    romÄĽ
    -0.07
    POSITIVE LOGITS
     Consumer
    0.08
     consumer
    0.08
     customer
    0.07
     consumers
    0.07
     customers
    0.06
     Customer
    0.06
     Consumers
    0.06
     firms
    0.06
    Consumer
    0.06
    org
    0.06
    Activations Density 0.012%

    No Known Activations