© 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. 5647
    Prev
    Next
    INDEX
    Explanations

    references to legal entities, responsibilities, and potentially liabilties in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ï¼Īå¹³æĪIJ
    -0.09
    .updateDynamic
    -0.08
    ainen
    -0.07
    lası
    -0.07
    ollow
    -0.07
    ÏĦια
    -0.07
    (åľŁ
    -0.07
    GuidId
    -0.07
    ezier
    -0.07
    (çģ«
    -0.07
    POSITIVE LOGITS
     include
    0.09
     themselves
    0.08
     includes
    0.07
     name
    0.07
    include
    0.07
     known
    0.07
     عبارت
    0.06
     names
    0.06
     consists
    0.06
     Includes
    0.06
    Activations Density 0.063%

    No Known Activations