© 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. 26939
    Prev
    Next
    INDEX
    Explanations

    criticisms or drawbacks of features in electronic devices

    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
    ære
    -0.07
     célib
    -0.07
    inux
    -0.07
    acus
    -0.06
    ahat
    -0.06
    боÑĤ
    -0.06
     plá
    -0.06
     odst
    -0.06
    .Contracts
    -0.06
     Liter
    -0.06
    POSITIVE LOGITS
     usable
    0.07
     useful
    0.07
     usefulness
    0.07
     limited
    0.07
    _integration
    0.07
     function
    0.07
    ลา
    0.07
     actually
    0.06
     practical
    0.06
     æ©
    0.06
    Activations Density 0.028%

    No Known Activations