© 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. 108776
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal arguments and claims

    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
    lage
    -0.09
    .lex
    -0.08
    eree
    -0.07
    ̧
    -0.07
    oden
    -0.07
    pton
    -0.07
    eyen
    -0.07
    lez
    -0.07
    ابÙĩ
    -0.07
     Lar
    -0.07
    POSITIVE LOGITS
     above
    0.16
    above
    0.14
     Above
    0.13
     ABOVE
    0.12
    Above
    0.12
    以ä¸Ĭ
    0.10
    _above
    0.10
    bove
    0.10
     foregoing
    0.09
     sentence
    0.09
    Activations Density 0.056%

    No Known Activations