© 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. 4069
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ongoing relationships or 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
    aph
    -0.06
    _Renderer
    -0.06
    marvin
    -0.06
     addCriterion
    -0.06
    oun
    -0.06
    asics
    -0.06
     Reputation
    -0.06
    kov
    -0.06
    ekyll
    -0.06
    licken
    -0.06
    POSITIVE LOGITS
     contact
    0.08
     Maint
    0.07
     manten
    0.07
     contacts
    0.07
     maintaining
    0.07
     maintains
    0.07
    èģĶç³»
    0.07
     communication
    0.07
     Contacts
    0.07
     maintain
    0.07
    Activations Density 0.025%

    No Known Activations