© 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. 123274
    Prev
    Next
    INDEX
    Explanations

    arguments related to laws and 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
    atten
    -0.08
    boru
    -0.07
    olini
    -0.07
    znam
    -0.07
    ëįķ
    -0.07
    inesis
    -0.07
    _LARGE
    -0.07
    大åħ¨
    -0.07
    iom
    -0.07
    åĸľ
    -0.07
    POSITIVE LOGITS
     counter
    0.10
     counters
    0.10
     countered
    0.09
     naopak
    0.09
     disagrees
    0.08
    counter
    0.08
     Counter
    0.08
     disagree
    0.07
     disputed
    0.07
     opposite
    0.07
    Activations Density 0.026%

    No Known Activations