© 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. 26848
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial implications and regulatory issues

    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
    üz
    -0.09
     поба
    -0.09
    quier
    -0.08
    eniz
    -0.08
    alars
    -0.08
    ikat
    -0.08
     nues
    -0.08
    ASI
    -0.07
    loquent
    -0.07
    stroy
    -0.07
    POSITIVE LOGITS
    0.06
    :↵
    0.06
    .sync
    0.05
    ;;↵
    0.05
    15
    0.05
     rental
    0.05
    417
    0.05
     ÙĪØ£ÙĨ
    0.05
     conduct
    0.05
     unreasonable
    0.05
    Activations Density 0.003%

    No Known Activations