© 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. 69225
    Prev
    Next
    INDEX
    Explanations

    references to legal resources and educational materials related to criminal law

    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
    anko
    -0.06
    éĻµ
    -0.06
     setDescription
    -0.06
    еÑĦ
    -0.06
    нÑĶ
    -0.06
    ython
    -0.06
     Synopsis
    -0.06
     Courier
    -0.06
     py
    -0.05
    challenge
    -0.05
    POSITIVE LOGITS
     articles
    0.10
    /articles
    0.09
     resources
    0.09
     knowledge
    0.09
     guides
    0.08
     tips
    0.08
     Articles
    0.08
     resource
    0.08
    tips
    0.08
    articles
    0.08
    Activations Density 0.052%

    No Known Activations