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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 126044
    Prev
    Next
    INDEX
    Explanations

    instances of the word "quirky" and its variations

    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
    illon
    -0.07
    701
    -0.06
    lad
    -0.06
    argin
    -0.06
    riz
    -0.06
    aan
    -0.06
    .exchange
    -0.06
    nings
    -0.06
    bast
    -0.06
    ipa
    -0.06
    POSITIVE LOGITS
    -fontawesome
    0.08
    ymb
    0.06
    -ios
    0.06
    AGO
    0.06
     resumes
    0.06
    tty
    0.06
    ıt
    0.06
    CellValue
    0.06
    NESS
    0.06
     IOCTL
    0.06
    Activations Density 0.001%

    No Known Activations