© 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. 56688
    Prev
    Next
    INDEX
    Explanations

    terms related to air or aerodynamics

    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
     Eugene
    -0.07
    pole
    -0.07
    ishi
    -0.07
    errupted
    -0.07
    odi
    -0.07
    amak
    -0.07
    arrant
    -0.07
    abcdefghijklmnop
    -0.07
    .WaitFor
    -0.07
    ردÙĩ
    -0.07
    POSITIVE LOGITS
    waves
    0.09
    bnb
    0.08
     air
    0.06
    finity
    0.06
    tel
    0.06
    -air
    0.06
    ikk
    0.06
    리ìĸ´
    0.06
     Cush
    0.06
    360
    0.06
    Activations Density 0.025%

    No Known Activations