© 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. 125207
    Prev
    Next
    INDEX
    Explanations

    references to specific aircraft manufacturers and models

    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
    /Peak
    -0.08
    nown
    -0.07
    ãĥ³ãĤ¬
    -0.07
    erving
    -0.07
    ISE
    -0.07
    ajor
    -0.06
    aghetti
    -0.06
    ebin
    -0.06
    боÑĢа
    -0.06
    abinet
    -0.06
    POSITIVE LOGITS
    538
    0.07
    y
    0.07
    ilian
    0.06
    alle
    0.06
    waves
    0.06
     Modular
    0.06
     heav
    0.06
    /videos
    0.06
    /software
    0.06
    istle
    0.06
    Activations Density 0.004%

    No Known Activations