© 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. 22-LLAMASCOPE-RES-131K
    11. 3953
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions affiliated with religious beliefs

    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
    çĽijåIJ¬é¡µéĿ¢
    -0.10
    iddet
    -0.09
    éĺħ读次æķ°
    -0.09
    ë¨
    -0.09
    -------------</
    -0.09
    ëĶĶìĭľ
    -0.09
    .opensource
    -0.09
     mesel
    -0.09
    волÑı
    -0.08
    eus
    -0.08
    POSITIVE LOGITS
     modern
    0.07
     pretty
    0.07
     normal
    0.07
    0.06
     official
    0.06
     tens
    0.06
     m
    0.06
     amid
    0.06
     lately
    0.06
     subdiv
    0.06
    Activations Density 0.000%

    No Known Activations