© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 89096
    Prev
    Next
    INDEX
    Explanations

    occurrences of the article "the"

    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
     sice
    -0.08
    alth
    -0.07
     nackte
    -0.07
    Traits
    -0.07
    ëĶ©
    -0.07
    incr
    -0.07
    ichen
    -0.06
    oled
    -0.06
    hani
    -0.06
    oster
    -0.06
    POSITIVE LOGITS
     reality
    0.07
     ÑĦакÑĤ
    0.07
     really
    0.07
     jury
    0.07
     mere
    0.07
    ãģĿãĤĮãģ¯
    0.07
     fact
    0.07
    tern
    0.07
    tery
    0.06
    ATO
    0.06
    Activations Density 0.047%

    No Known Activations