© 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. 84476
    Prev
    Next
    INDEX
    Explanations

    references related to political dynamics and financial transactions

    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
    andle
    -0.08
    ä¾
    -0.08
    artz
    -0.07
    icari
    -0.07
    ugin
    -0.07
    reamble
    -0.07
    oldt
    -0.07
     Ngh
    -0.07
    cmc
    -0.07
    duc
    -0.07
    POSITIVE LOGITS
     al
    0.06
     Sky
    0.06
     Al
    0.06
    <context
    0.06
    ooth
    0.06
     ISI
    0.06
    defgroup
    0.06
     Mast
    0.06
     recruits
    0.06
    flix
    0.06
    Activations Density 0.007%

    No Known Activations