© 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. 5-LLAMASCOPE-RES-131K
    11. 125588
    Prev
    Next
    INDEX
    Explanations

    terms related to propellers in aviation technology

    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
    itler
    -0.08
    ipur
    -0.07
    668
    -0.06
    ossier
    -0.06
    iba
    -0.06
     DISPATCH
    -0.06
    qa
    -0.06
     Bilg
    -0.06
    emin
    -0.06
    ulen
    -0.06
    POSITIVE LOGITS
    endoza
    0.07
    lassen
    0.07
    zoek
    0.06
    yle
    0.06
    Ī
    0.06
    243
    0.06
    UME
    0.06
    èĬ¬
    0.06
    ymph
    0.06
    SSI
    0.06
    Activations Density 0.002%

    No Known Activations