© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70262
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal claims and proceedings

    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
     Fresno
    -0.07
     Missouri
    -0.07
     Tulsa
    -0.07
     colorWith
    -0.07
     Memphis
    -0.07
    ypress
    -0.07
    ATO
    -0.07
     Rural
    -0.06
    _UNICODE
    -0.06
    htdocs
    -0.06
    POSITIVE LOGITS
     Massachusetts
    0.29
     Boston
    0.28
    Boston
    0.25
     Celtics
    0.20
     Maine
    0.18
     Rhode
    0.18
     Harvard
    0.16
     NH
    0.16
     Worcester
    0.16
    achusetts
    0.15
    Activations Density 0.826%

    No Known Activations