© 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. 126148
    Prev
    Next
    INDEX
    Explanations

    the word "recently" and its various mentions

    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
    rab
    -0.07
     ↵↵
    -0.06
    eras
    -0.06
    æĸ¹éĿ¢
    -0.06
    oose
    -0.06
     tomorrow
    -0.06
    ãĥ¼ãĥķ
    -0.06
    oles
    -0.06
    oui
    -0.06
    bstract
    -0.06
    POSITIVE LOGITS
    iddet
    0.09
    woke
    0.08
    tep
    0.07
    infeld
    0.07
    _CHUNK
    0.06
     Kens
    0.06
    took
    0.06
    IPHER
    0.06
    unos
    0.06
     fatt
    0.06
    Activations Density 0.011%

    No Known Activations