© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16723
    Prev
    Next
    INDEX
    Explanations

    historical references and contexts related to the Byzantine Empire

    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
    akk
    -0.08
    å±¥
    -0.08
    abant
    -0.07
    midi
    -0.07
    매
    -0.07
    strom
    -0.07
    #Region
    -0.07
     ков
    -0.07
    Ïħγ
    -0.07
    locator
    -0.07
    POSITIVE LOGITS
     patron
    0.09
     culture
    0.08
     propag
    0.07
     tolerance
    0.07
     sponsor
    0.07
     sponsoring
    0.07
     Renaissance
    0.06
     cultural
    0.06
     tolerant
    0.06
     grand
    0.06
    Activations Density 0.013%

    No Known Activations