© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90823
    Prev
    Next
    INDEX
    Explanations

    terms related to air and its movement

    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
     внÑĥÑĤ
    -0.07
     Concurrent
    -0.07
    childs
    -0.07
     nomine
    -0.06
    ureau
    -0.06
    ç¿°
    -0.06
    inue
    -0.06
     ÑģобоÑİ
    -0.06
    irthday
    -0.06
    iali
    -0.06
    POSITIVE LOGITS
    /on
    0.07
    /at
    0.06
     near
    0.06
    Wunused
    0.06
    pf
    0.06
    be
    0.06
     Gerald
    0.05
    near
    0.05
    355
    0.05
    osphere
    0.05
    Activations Density 0.024%

    No Known Activations