© 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. 22-LLAMASCOPE-RES-131K
    11. 4247
    Prev
    Next
    INDEX
    Explanations

    references to legal acts and constitutional amendments

    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
    oa
    -0.08
    itm
    -0.07
    wik
    -0.06
    озв
    -0.06
    aseline
    -0.06
    tank
    -0.06
    eson
    -0.06
    etes
    -0.06
    $title
    -0.06
    maj
    -0.06
    POSITIVE LOGITS
     Regulations
    0.07
     Amendment
    0.07
     Bill
    0.07
     BILL
    0.07
    USART
    0.06
    apot
    0.06
     bill
    0.06
    Am
    0.06
     Rug
    0.06
     regulations
    0.06
    Activations Density 0.002%

    No Known Activations