© 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. 57228
    Prev
    Next
    INDEX
    Explanations

    terms related to structural design and engineering

    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
    åľĪ
    -0.07
     kolo
    -0.07
    unds
    -0.07
     eskort
    -0.06
    =ax
    -0.06
     axial
    -0.06
     Retrieves
    -0.06
     पह
    -0.06
    ilib
    -0.06
    _VENDOR
    -0.06
    POSITIVE LOGITS
     load
    0.08
     cant
    0.08
     beam
    0.08
    Beam
    0.07
     Beam
    0.07
     beams
    0.07
     sway
    0.07
     jo
    0.07
     Loads
    0.07
     building
    0.07
    Activations Density 0.005%

    No Known Activations