© 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. 116385
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to custody and support orders

    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
    TickCount
    -0.08
    lemn
    -0.07
    argar
    -0.07
    gard
    -0.07
    mpr
    -0.07
    anitize
    -0.07
     aqu
    -0.07
    جاد
    -0.07
    aign
    -0.07
    )const
    -0.07
    POSITIVE LOGITS
     hereby
    0.15
     shall
    0.10
     SHALL
    0.09
     Shall
    0.08
    shall
    0.07
     now
    0.07
    ise
    0.07
     hence
    0.07
     forever
    0.07
     tÃŃmto
    0.06
    Activations Density 0.017%

    No Known Activations