© 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. 74659
    Prev
    Next
    INDEX
    Explanations

    references to international coalitions and agreements

    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
    íĮ
    -0.08
    finder
    -0.08
    oldemort
    -0.07
    toi
    -0.07
    continent
    -0.07
    cea
    -0.07
    ä¸ĢåĮº
    -0.07
     Böl
    -0.06
     asia
    -0.06
    quete
    -0.06
    POSITIVE LOGITS
    é¢
    0.06
    adaki
    0.06
    à¤Łà¤°
    0.06
    Outcome
    0.06
    avel
    0.06
    .getElements
    0.06
     resc
    0.06
     Ticaret
    0.05
     Republic
    0.05
    134
    0.05
    Activations Density 0.016%

    No Known Activations