© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 86139
    Prev
    Next
    INDEX
    Explanations

    financial benefits and economic impacts related to Northern Ireland

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    stery
    -0.07
    ëħĢ
    -0.07
    PullParser
    -0.06
    éĩĩ
    -0.06
    alem
    -0.06
    fraction
    -0.06
    lage
    -0.06
     subsystem
    -0.06
     Sister
    -0.06
     Bonnie
    -0.06
    POSITIVE LOGITS
    enko
    0.06
    igan
    0.06
    ±ä¹IJ
    0.06
    taire
    0.06
    Validators
    0.06
    DMI
    0.06
    Ñıд
    0.06
    ara
    0.06
     بÙĪابة
    0.06
    èĬĻ
    0.06
    Activations Density 0.009%

    No Known Activations