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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4060
    Prev
    Next
    INDEX
    Explanations

    references to judicial dissenting opinions and their authors

    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
    olf
    -0.08
    uset
    -0.07
    åĪ¶
    -0.07
    ç»Ń
    -0.06
    avit
    -0.06
    HasBeen
    -0.06
     HÃłng
    -0.06
    оÑĤов
    -0.06
    اشة
    -0.06
    attery
    -0.06
    POSITIVE LOGITS
     dissent
    0.09
     onHide
    0.07
    æĦıè§ģ
    0.07
     advert
    0.06
    CRM
    0.06
    ÏĦÎŃ
    0.06
     op
    0.06
     joined
    0.06
    idente
    0.06
    issent
    0.06
    Activations Density 0.016%

    No Known Activations