© 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. 9-LLAMASCOPE-RES-131K
    11. 95326
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "of" 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
    elmet
    -0.08
    alyzed
    -0.08
    nia
    -0.07
    edBy
    -0.07
    ted
    -0.07
    pus
    -0.07
    fir
    -0.07
    еÑĢÑĪ
    -0.07
    elpers
    -0.07
    istik
    -0.06
    POSITIVE LOGITS
    ابÙĩ
    0.07
     Feather
    0.06
    ÙĤب
    0.06
    #ad
    0.06
    kel
    0.06
     adjud
    0.05
    779
    0.05
    IMIT
    0.05
    600
    0.05
    çok
    0.05
    Activations Density 0.010%

    No Known Activations