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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 93588
    Prev
    Next
    INDEX
    Explanations

    references to judicial or legal relationships and interactions

    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
    swick
    -0.08
    ãģ«è¦ĭ
    -0.07
    malar
    -0.07
     proÄį
    -0.07
    ZIP
    -0.07
    rů
    -0.07
    minster
    -0.07
    rone
    -0.07
    bÃŃ
    -0.07
     posix
    -0.06
    POSITIVE LOGITS
     directly
    0.09
     subjects
    0.07
     opposite
    0.07
     direct
    0.07
     lit
    0.07
     cud
    0.06
     lobby
    0.06
     DIRECT
    0.06
     industry
    0.06
    .uc
    0.06
    Activations Density 0.013%

    No Known Activations