© 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. 42543
    Prev
    Next
    INDEX
    Explanations

    references to graphical or design elements, particularly in a procedural context

    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
     akadem
    -0.09
     modne
    -0.08
    inou
    -0.08
    .createComponent
    -0.08
    eydi
    -0.08
    <quote
    -0.08
    avaÅŁ
    -0.07
     proje
    -0.07
    (=)
    -0.07
    βι
    -0.07
    POSITIVE LOGITS
    lier
    0.06
     pay
    0.06
    âĢ¦↵
    0.06
     Fleming
    0.06
     remaining
    0.06
     again
    0.06
     next
    0.05
     reset
    0.05
    02
    0.05
    ´Ģ
    0.05
    Activations Density 0.130%

    No Known Activations