© 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. 108775
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases related to processes or evaluations in scientific or medical contexts

    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
    žel
    -0.07
    vu
    -0.07
    ÃŃrk
    -0.07
    縮
    -0.07
    abei
    -0.07
    wald
    -0.06
     erv
    -0.06
     -*-č↵
    -0.06
     sig
    -0.06
    kit
    -0.06
    POSITIVE LOGITS
    azy
    0.06
     Hastings
    0.06
    htm
    0.05
     nail
    0.05
    ollider
    0.05
    oreach
    0.05
     ((__
    0.05
     vr
    0.05
    æį·
    0.05
     Allan
    0.05
    Activations Density 0.001%

    No Known Activations