© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-LLAMASCOPE-RES-131K
    11. 97212
    Prev
    Next
    INDEX
    Explanations

    specific phrases or structures indicating relationships and connections

    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
    iesen
    -0.07
     printk
    -0.07
     md
    -0.06
    åįĺ
    -0.06
    anta
    -0.06
    zet
    -0.05
    allen
    -0.05
    aban
    -0.05
    ire
    -0.05
     intrusive
    -0.05
    POSITIVE LOGITS
     ones
    0.09
    erty
    0.07
    LETE
    0.07
    },{↵
    0.07
    ovol
    0.07
     гла
    0.07
    à¥įरम
    0.07
    VRT
    0.07
    HLT
    0.07
     Entr
    0.07
    Activations Density 0.034%

    No Known Activations