© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126104
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ignore" 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
    ago
    -0.08
    agli
    -0.08
    lopedia
    -0.08
    Ậ
    -0.07
    ÃĦŸ
    -0.07
    emiz
    -0.07
    ëł´
    -0.07
    _handlers
    -0.07
    каÑģ
    -0.07
    wik
    -0.07
    POSITIVE LOGITS
     altogether
    0.09
    æİī
    0.08
    ance
    0.07
     ignore
    0.07
     Ignore
    0.06
    ác
    0.06
     warnings
    0.06
     deadline
    0.06
     stip
    0.06
     Completely
    0.06
    Activations Density 0.010%

    No Known Activations