© 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. 125436
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "are."

    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
    536
    -0.07
    559
    -0.07
    artment
    -0.07
    (!_
    -0.06
    ãĤĥ
    -0.06
    imensional
    -0.06
    ä¸ĢåĢĭ
    -0.06
    morgan
    -0.06
    .re
    -0.06
    ist
    -0.06
    POSITIVE LOGITS
     hereby
    0.08
    /w
    0.07
    nt
    0.07
    ospace
    0.07
    asio
    0.07
    ABEL
    0.07
    WithPath
    0.06
     Elk
    0.06
    ãĥªãĥ³ãĤ°
    0.06
    nde
    0.06
    Activations Density 0.293%

    No Known Activations