© 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. 15-LLAMASCOPE-RES-131K
    11. 61286
    Prev
    Next
    INDEX
    Explanations

    the word "both" and its variations in context

    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
     Sez
    -0.07
    chet
    -0.07
    asses
    -0.07
    ارÛĮ
    -0.07
    ema
    -0.06
     Spo
    -0.06
    apyrus
    -0.06
    uhl
    -0.06
    [](
    -0.06
    iras
    -0.06
    POSITIVE LOGITS
    cripts
    0.08
     BOTH
    0.07
    'RE
    0.06
    lyph
    0.06
    úsqueda
    0.06
     áo
    0.06
    both
    0.06
     Cart
    0.06
    Overlap
    0.06
    viders
    0.06
    Activations Density 0.017%

    No Known Activations