© 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. 26997
    Prev
    Next
    INDEX
    Explanations

    legal terms related to liability and damages

    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
    áte
    -0.07
    arah
    -0.07
    ilip
    -0.07
    èµĦ
    -0.07
    /topics
    -0.07
    stract
    -0.07
    Traits
    -0.06
    hci
    -0.06
    woke
    -0.06
    mpr
    -0.06
    POSITIVE LOGITS
     pent
    0.07
    ecut
    0.06
    rist
    0.06
     GSM
    0.06
    uela
    0.06
     NotSupportedException
    0.06
     ///</
    0.06
    pector
    0.06
    ircle
    0.06
    iente
    0.06
    Activations Density 0.000%

    No Known Activations