© 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. 5-LLAMASCOPE-RES-131K
    11. 125713
    Prev
    Next
    INDEX
    Explanations

    terms related to Turkish culture and literature

    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
    oment
    -0.06
    áty
    -0.06
     Ø´ÙĪ
    -0.06
    еÑħ
    -0.06
    onia
    -0.06
    DD
    -0.06
    fty
    -0.06
    RECT
    -0.06
    راÙģ
    -0.06
    ergus
    -0.06
    POSITIVE LOGITS
    vap
    0.07
    ettes
    0.06
    ars
    0.06
     Hay
    0.06
     Mandal
    0.06
     Newest
    0.06
    ndef
    0.06
    precated
    0.06
     æ¹
    0.06
    iye
    0.06
    Activations Density 0.293%

    No Known Activations