© 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. 84346
    Prev
    Next
    INDEX
    Explanations

    instances of the word "isn't" and similar negations related to existence

    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
    ÃĹ↵↵
    -0.12
    (=)
    -0.11
    .scalablytyped
    -0.11
    ÑĤÑİ
    -0.10
    ÙĬÙĦا
    -0.10
    .Dictionary
    -0.10
    ÑģоÑĤ
    -0.10
    _LP
    -0.10
    .EventType
    -0.09
    _Long
    -0.09
    POSITIVE LOGITS
    ,
    0.09
    ...↵
    0.09
    ...
    0.08
    ..↵
    0.08
    :
    0.08
     and
    0.08
    âĢ¦
    0.07
    âĢ¦↵
    0.07
    .
    0.07
    ..
    0.07
    Activations Density 0.353%

    No Known Activations