© 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. 129504
    Prev
    Next
    INDEX
    Explanations

    instances of the word "two" and related phrases indicating duality or pairs

    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
    fold
    -0.08
    ../../
    -0.07
    áÅĻ
    -0.07
     circumference
    -0.07
    th
    -0.07
    ../../../../
    -0.06
    ά
    -0.06
     surrounding
    -0.06
    iper
    -0.06
    oured
    -0.06
    POSITIVE LOGITS
     halves
    0.12
     extremes
    0.09
     sides
    0.08
    gether
    0.08
    ATTER
    0.08
     sexes
    0.07
    nd
    0.07
     Kore
    0.07
     opposite
    0.07
    ards
    0.07
    Activations Density 0.092%

    No Known Activations