Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44089
    Prev
    Next
    INDEX
    Explanations

    locations and names of courts

    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
     liter
    -0.07
    uml
    -0.07
    ubit
    -0.07
    ledik
    -0.06
    pyx
    -0.06
    toolbox
    -0.06
    ubits
    -0.06
     municipalities
    -0.06
    Hang
    -0.06
    .memo
    -0.06
    POSITIVE LOGITS
     Court
    0.15
    Court
    0.12
     court
    0.10
    ourt
    0.10
     Crown
    0.10
     Cour
    0.10
     Courts
    0.10
     courthouse
    0.09
     Ct
    0.09
    court
    0.08
    Activations Density 0.005%

    No Known Activations