© 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. 76351
    Prev
    Next
    INDEX
    Explanations

    terms related to the functioning and management of systems or machinery

    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
    mobx
    -0.07
    morgan
    -0.06
     ÑĢаÐ
    -0.06
    ìŀIJìĿ¸
    -0.06
    ../../../
    -0.06
    boarding
    -0.06
     Dump
    -0.06
    oplay
    -0.06
    ming
    -0.06
    _ATOMIC
    -0.06
    POSITIVE LOGITS
    身ä¸Ĭ
    0.07
    -wide
    0.07
    atsby
    0.06
    achuset
    0.06
    StateManager
    0.06
    uzzer
    0.06
    èĩªèº«
    0.06
    stagram
    0.06
    ÑĢÑıдÑĥ
    0.06
     INCIDENTAL
    0.06
    Activations Density 0.054%

    No Known Activations