© 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. 17-LLAMASCOPE-RES-131K
    11. 5906
    Prev
    Next
    INDEX
    Explanations

    references to the Israeli-Palestinian conflict and its related complexities

    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
     Gaut
    -0.07
    bert
    -0.07
    gom
    -0.07
    ovit
    -0.07
     etc
    -0.07
    CTION
    -0.06
    овеÑĢ
    -0.06
    Ral
    -0.06
    ÃŃsto
    -0.06
    etwork
    -0.06
    POSITIVE LOGITS
     eskort
    0.07
    ]=>
    0.07
     HOLDERS
    0.06
    é®
    0.06
    549
    0.06
    íĶ
    0.06
     Blowjob
    0.06
     Ekim
    0.06
    ADS
    0.06
     ç¥
    0.06
    Activations Density 0.017%

    No Known Activations