© 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. 88019
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to microscopy and nanoscale systems

    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
    emo
    -0.07
     McKenzie
    -0.07
    eg
    -0.06
    myModal
    -0.06
     eg
    -0.06
    /misc
    -0.06
    ognition
    -0.06
    rupa
    -0.06
    мÑĸн
    -0.06
     memor
    -0.06
    POSITIVE LOGITS
     Rarity
    0.08
     éĹ
    0.07
    VL
    0.06
     tricks
    0.06
     tiny
    0.06
     pun
    0.06
     measuring
    0.06
    omain
    0.06
    146
    0.06
     pits
    0.06
    Activations Density 0.005%

    No Known Activations