© 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. 17-LLAMASCOPE-RES-131K
    11. 88538
    Prev
    Next
    INDEX
    Explanations

    specific geographical locations and proper nouns

    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
    ipp
    -0.08
     Underground
    -0.06
     reverse
    -0.06
    åĨł
    -0.06
     ip
    -0.06
    azzi
    -0.06
    ippy
    -0.06
    ewis
    -0.06
    iki
    -0.06
    ogn
    -0.05
    POSITIVE LOGITS
    ÅĻez
    0.07
    ÙĪراÙĨ
    0.07
    ternet
    0.07
    PRESENT
    0.07
    å±¥
    0.07
    serter
    0.07
    _attach
    0.07
    utedString
    0.07
    chwitz
    0.07
    ylum
    0.07
    Activations Density 0.002%

    No Known Activations