© 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. 39812
    Prev
    Next
    INDEX
    Explanations

    instances of the word "The" as well as other definite articles and pronouns in the text

    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
    iton
    -0.07
    puts
    -0.07
    POSE
    -0.06
     generation
    -0.06
    lamp
    -0.06
    elib
    -0.06
    zimmer
    -0.06
    âĢİ
    -0.06
    usk
    -0.06
    recent
    -0.06
    POSITIVE LOGITS
     result
    0.09
     then
    0.08
     ensuing
    0.08
    ãĤº
    0.07
     resulting
    0.07
     subsequent
    0.07
     Result
    0.07
    -result
    0.07
    ãģĻãĤĭãģ¨
    0.06
    akan
    0.06
    Activations Density 0.042%

    No Known Activations