© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 128744
    Prev
    Next
    INDEX
    Explanations

    terms related to process automation and management

    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
    _RD
    -0.07
    inflate
    -0.07
    nev
    -0.07
     Arabia
    -0.07
    adius
    -0.06
     Amateur
    -0.06
    骨
    -0.06
    ADR
    -0.06
    chooser
    -0.06
    Ïģιν
    -0.06
    POSITIVE LOGITS
     bots
    0.07
    arial
    0.07
     Garrison
    0.06
     Human
    0.06
    人éĸĵ
    0.06
     execut
    0.06
    BoundingClientRect
    0.06
    Exec
    0.06
    human
    0.06
     bot
    0.06
    Activations Density 0.001%

    No Known Activations