© 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. 94172
    Prev
    Next
    INDEX
    Explanations

    phrases related to compliance with laws or regulations

    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
    oleon
    -0.07
    anke
    -0.07
    velt
    -0.07
    fold
    -0.07
    onto
    -0.07
    mite
    -0.06
    473
    -0.06
    ünchen
    -0.06
    .RunWith
    -0.06
    ktion
    -0.06
    POSITIVE LOGITS
     past
    0.07
    ifecycle
    0.06
    ters
    0.06
     Denn
    0.06
    _ptrs
    0.06
    apers
    0.06
     tl
    0.06
     nhau
    0.06
    å»
    0.06
     previous
    0.05
    Activations Density 0.006%

    No Known Activations