© 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. 17179
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to aviation and filming

    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
     atomic
    -0.08
    jez
    -0.07
    Atomic
    -0.07
     Atomic
    -0.07
    atomic
    -0.07
     Automobile
    -0.07
    rette
    -0.06
     DRIVER
    -0.06
    ÑĢин
    -0.06
    iode
    -0.06
    POSITIVE LOGITS
     Sik
    0.08
     helicopters
    0.08
    ìĬĪ
    0.07
     ceiling
    0.07
    /operators
    0.07
     Operators
    0.07
     civil
    0.07
     operator
    0.07
     rotor
    0.06
     FAA
    0.06
    Activations Density 0.006%

    No Known Activations