© 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. 9-LLAMASCOPE-RES-131K
    11. 94132
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to semiconductor manufacturing and specifications

    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
    iaux
    -0.06
    igin
    -0.06
    imitive
    -0.06
     Till
    -0.05
     ho
    -0.05
     Wright
    -0.05
    æ
    -0.05
     ز
    -0.05
     False
    -0.05
    ibu
    -0.05
    POSITIVE LOGITS
    à¥ĩण
    0.08
    icio
    0.08
    amiento
    0.07
    ãĥ¼ãĥª
    0.07
    amientos
    0.07
    Äĩe
    0.07
     доÑģÑĤ
    0.07
    lder
    0.07
     <<=
    0.07
    .Reporting
    0.07
    Activations Density 0.001%

    No Known Activations