© 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 EvalsExportsinterp-engineNEWAPI 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. 2134
    Prev
    Next
    INDEX
    Explanations

    the word "but" and variations in phrasing that indicate contrast or exceptions

    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
    ëĵł
    -0.07
    обÑĢаз
    -0.06
    umeric
    -0.06
    ieux
    -0.06
    ip
    -0.06
    ÏĮÏģ
    -0.06
    orno
    -0.06
    ni
    -0.06
     bitir
    -0.06
     recess
    -0.06
    POSITIVE LOGITS
    ãģĹãģĭãģĹ
    0.08
    mere
    0.08
     However
    0.08
     majority
    0.07
    tsky
    0.07
     jedoch
    0.07
    However
    0.07
     Majority
    0.07
    exas
    0.07
     however
    0.07
    Activations Density 0.042%

    No Known Activations