© 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. 15604
    Prev
    Next
    INDEX
    Explanations

    instances of the word "whilst" 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
    s
    -0.16
    nt
    -0.09
    ãģĦãĤĭ
    -0.09
    /or
    -0.09
    ÏĤ
    -0.08
    hips
    -0.08
    ãĤ¥
    -0.08
    er
    -0.08
    ish
    -0.08
    /is
    -0.07
    POSITIVE LOGITS
    forth
    0.12
    raq
    0.09
    ãģªãģĦ
    0.09
     обÑĢазом
    0.08
    entimes
    0.08
    NewLabel
    0.08
    prav
    0.07
    ìĦľëĬĶ
    0.07
    quer
    0.07
    iquid
    0.07
    Activations Density 0.012%

    No Known Activations