© 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. 83115
    Prev
    Next
    INDEX
    Explanations

    references to the Supreme Court and its prior decisions

    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
    arus
    -0.07
    ête
    -0.06
    ÅĻes
    -0.06
    rost
    -0.06
    ?action
    -0.06
     Bale
    -0.06
    mpl
    -0.06
    onte
    -0.06
    iphy
    -0.06
     Ùħض
    -0.06
    POSITIVE LOGITS
     Bench
    0.07
     preced
    0.07
     bench
    0.07
    ients
    0.07
    \Migration
    0.06
     Inspiration
    0.06
     Hä
    0.06
    Binder
    0.06
     precedent
    0.06
    Unmarshaller
    0.06
    Activations Density 0.009%

    No Known Activations