© 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. 127608
    Prev
    Next
    INDEX
    Explanations

    the word "is" and its variants in various contexts

    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
    edin
    -0.07
    aga
    -0.07
    ungen
    -0.06
    chwitz
    -0.06
    982
    -0.06
    ohn
    -0.06
    uer
    -0.06
    eda
    -0.06
    628
    -0.06
    å±
    -0.06
    POSITIVE LOGITS
    ÙĬار
    0.06
    elsif
    0.06
    ë´IJ
    0.06
    Ñĥда
    0.06
    ajor
    0.06
    'gc
    0.06
    ãĥ¼ãĤ¹
    0.06
    inkle
    0.06
    _mE
    0.06
    åĥķ
    0.06
    Activations Density 0.015%

    No Known Activations