© 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. 80920
    Prev
    Next
    INDEX
    Explanations

    words related to property regulations and limitations

    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
    akis
    -0.06
    Lab
    -0.06
    plete
    -0.06
    볨
    -0.06
    kol
    -0.06
    amer
    -0.06
    cala
    -0.06
     ilg
    -0.06
     sovere
    -0.06
     spill
    -0.06
    POSITIVE LOGITS
    /right
    0.07
    ee
    0.07
    ivent
    0.07
    heiro
    0.07
     rights
    0.07
     Sew
    0.07
    eview
    0.07
    ên
    0.06
    Enumerable
    0.06
     exerc
    0.06
    Activations Density 0.002%

    No Known Activations