© 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. 14091
    Prev
    Next
    INDEX
    Explanations

    mentions of company details and affiliations

    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
    ori
    -0.07
    ysi
    -0.07
    âĢĮØ¢
    -0.06
    ilim
    -0.06
    pter
    -0.06
    itto
    -0.06
    .web
    -0.06
     OTHERWISE
    -0.06
    orado
    -0.06
    à¥Ģà¤Ĥ
    -0.06
    POSITIVE LOGITS
     job
    0.07
     position
    0.07
    à¤Ĺल
    0.07
    pec
    0.07
    uggle
    0.07
     opportunity
    0.06
    ÏĦζ
    0.06
    positions
    0.06
    .Summary
    0.06
     exciting
    0.06
    Activations Density 0.020%

    No Known Activations