© 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. 41096
    Prev
    Next
    INDEX
    Explanations

    scenes and interactions involving groups or gatherings

    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
     einer
    -0.07
    aint
    -0.07
     hereby
    -0.07
     algun
    -0.07
    rame
    -0.07
    aug
    -0.06
    ][_
    -0.06
    .$.
    -0.06
    ascus
    -0.06
    .scalajs
    -0.06
    POSITIVE LOGITS
     etc
    0.07
    etc
    0.07
    ased
    0.07
    ãģĤãģ®
    0.07
    iken
    0.06
    uka
    0.06
    éĤ£ä¸ª
    0.06
    änd
    0.06
    Liked
    0.06
    imeline
    0.06
    Activations Density 0.098%

    No Known Activations