© 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. 31456
    Prev
    Next
    INDEX
    Explanations

    deep personal reflections and struggles

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     yourselves
    -0.08
     sizi
    -0.07
    aint
    -0.07
    etch
    -0.06
    OrElse
    -0.06
    OrFail
    -0.06
    otch
    -0.06
    iq
    -0.06
    ecta
    -0.06
    tra
    -0.06
    POSITIVE LOGITS
     lately
    0.07
     myself
    0.07
     saya
    0.07
     my
    0.07
     mijn
    0.07
     lesson
    0.07
    让æĪij
    0.06
    .scalablytyped
    0.06
     maybe
    0.06
    raya
    0.06
    Activations Density 0.013%

    No Known Activations