© 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. 103883
    Prev
    Next
    INDEX
    Explanations

    narratives or descriptions related to testing and validation processes

    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
    -pic
    -0.07
    .extensions
    -0.06
    /control
    -0.06
    RESH
    -0.06
     Lehr
    -0.06
    -utils
    -0.06
    ÙĦÙĩ
    -0.06
    RenderingContext
    -0.06
     pesso
    -0.06
    -contrib
    -0.06
    POSITIVE LOGITS
     feedback
    0.09
    feedback
    0.09
     Feedback
    0.09
    Feedback
    0.08
     testing
    0.08
     stability
    0.08
     tested
    0.07
    ÑĪиб
    0.07
    -feedback
    0.07
     experience
    0.07
    Activations Density 0.036%

    No Known Activations