© 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. 116376
    Prev
    Next
    INDEX
    Explanations

    nouns related to specific categories and entities such as products, services, and places

    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
    pha
    -0.07
    alar
    -0.07
    cha
    -0.07
    ostel
    -0.06
    orts
    -0.06
    755
    -0.06
     ä¸
    -0.06
    анÑģи
    -0.06
    lech
    -0.06
    ahas
    -0.06
    POSITIVE LOGITS
     whose
    0.09
     that
    0.09
    andles
    0.07
     Meadow
    0.07
    ÙijÙı
    0.07
    quet
    0.07
    whose
    0.06
    ìĤ°
    0.06
    SCRIPTION
    0.06
    à¤Ĥध
    0.06
    Activations Density 0.078%

    No Known Activations