© 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. 5989
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal compliance and court decisions

    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
    oin
    -0.06
    amples
    -0.06
     Pur
    -0.06
    ugs
    -0.06
    itr
    -0.06
     universal
    -0.06
     candidates
    -0.06
     Mitar
    -0.06
     purs
    -0.06
     Schwartz
    -0.06
    POSITIVE LOGITS
     outcome
    0.10
     decision
    0.09
     ruling
    0.09
    outcome
    0.09
     victory
    0.08
    èĥľ
    0.08
    decision
    0.08
    ç»ĵæŀľ
    0.08
     decisions
    0.08
     findings
    0.08
    Activations Density 0.022%

    No Known Activations