© 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. 86867
    Prev
    Next
    INDEX
    Explanations

    references to specific objects or events

    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
    اÙĦا
    -0.07
     fisse
    -0.07
    ãĤĬãģ¨
    -0.07
     fis
    -0.06
     Fall
    -0.06
    ials
    -0.06
    ãĥ¬ãĥĥãĥĪ
    -0.06
    ould
    -0.06
    ovnÄĽ
    -0.06
     Equivalent
    -0.06
    POSITIVE LOGITS
    æĺĩ
    0.07
    à¸Īร
    0.07
     alone
    0.06
    reason
    0.06
     but
    0.06
     sondern
    0.06
    (<?
    0.06
    IRMWARE
    0.06
     بÙĦÚ©Ùĩ
    0.06
    ASTER
    0.06
    Activations Density 0.002%

    No Known Activations