© 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. 128174
    Prev
    Next
    INDEX
    Explanations

    phrases related to influences and properties of subjects or objects

    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
    opensource
    -0.07
     Drops
    -0.06
    γκα
    -0.06
    Щ
    -0.06
    adio
    -0.06
    adow
    -0.06
    lias
    -0.05
    ÏĦεÏģα
    -0.05
    ῶ
    -0.05
    ocene
    -0.05
    POSITIVE LOGITS
     inspiration
    0.13
     Inspiration
    0.09
     source
    0.07
     inspir
    0.07
     ideas
    0.07
    ander
    0.07
    ideo
    0.07
    source
    0.07
    undy
    0.07
    kaar
    0.07
    Activations Density 0.028%

    No Known Activations