© 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. 31657
    Prev
    Next
    INDEX
    Explanations

    terms related to endorsements and recommendations

    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
    terdam
    -0.06
    ãĥ³ãĥĦ
    -0.06
    itude
    -0.06
    аÑĢд
    -0.06
     Guard
    -0.06
     Zhu
    -0.06
    æľĽ
    -0.06
    Ñĥг
    -0.06
    akedown
    -0.06
    /new
    -0.06
    POSITIVE LOGITS
     nor
    0.08
    ses
    0.07
    oes
    0.07
    ittal
    0.07
    ãĤĩ
    0.06
     Scha
    0.06
    Firebase
    0.06
    interp
    0.06
    akin
    0.06
    arp
    0.06
    Activations Density 0.001%

    No Known Activations