© 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. 123488
    Prev
    Next
    INDEX
    Explanations

    sections of code comments or documentation

    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
     ziy
    -0.08
    ï¸ı
    -0.07
    IOC
    -0.07
    eworld
    -0.07
    nil
    -0.07
    391
    -0.07
    coes
    -0.07
    cores
    -0.07
    ekt
    -0.07
    VENTORY
    -0.06
    POSITIVE LOGITS
    BB
    0.07
    hack
    0.06
    vio
    0.06
     Fle
    0.06
     hy
    0.06
     hacks
    0.06
    ony
    0.06
     Orr
    0.06
     Maced
    0.06
     inc
    0.06
    Activations Density 0.000%

    No Known Activations