© 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. 4347
    Prev
    Next
    INDEX
    Explanations

    terms related to documents and reports, particularly in a legislative or historical context

    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
    .dll
    -0.06
     Licht
    -0.06
     pres
    -0.06
     bif
    -0.06
     levy
    -0.06
    ληÏĤ
    -0.06
     jinak
    -0.06
    žel
    -0.06
     conserv
    -0.06
     whom
    -0.06
    POSITIVE LOGITS
    831
    0.07
    883
    0.07
    ampa
    0.06
     Bulk
    0.06
    ÅĤu
    0.06
     âĢ¦↵↵
    0.06
    oblin
    0.06
    æĪª
    0.06
    query
    0.06
    ãģłãĤĪ
    0.06
    Activations Density 0.037%

    No Known Activations