© 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. 15-LLAMASCOPE-RES-131K
    11. 26848
    Prev
    Next
    INDEX
    Explanations

    references to museums and art exhibitions

    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
    гов
    -0.07
    olik
    -0.06
    ç´Ģ
    -0.06
    etails
    -0.06
    fetchAll
    -0.06
     Wasser
    -0.06
    arten
    -0.06
     microwave
    -0.06
    artner
    -0.06
     conventional
    -0.06
    POSITIVE LOGITS
    ahat
    0.06
    lect
    0.06
    lex
    0.06
     collections
    0.06
     Adolf
    0.06
     Automobile
    0.06
    ).__
    0.06
     bir
    0.06
    ius
    0.06
     Collections
    0.06
    Activations Density 0.004%

    No Known Activations