© 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. 1187
    Prev
    Next
    INDEX
    Explanations

    various types of credit card payment options

    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
    ylim
    -0.07
    angkan
    -0.07
    dum
    -0.07
    azzi
    -0.07
    282
    -0.07
    ombs
    -0.07
     ÛĮعÙĨÛĮ
    -0.07
    Ã
    -0.07
    olia
    -0.07
    ÑĥÑĢÑĥ
    -0.07
    POSITIVE LOGITS
     etc
    0.09
    etc
    0.07
    jpeg
    0.05
     Jog
    0.05
     Vive
    0.05
    fmt
    0.05
     Revenge
    0.05
    vetica
    0.05
    IENT
    0.05
     Trouble
    0.05
    Activations Density 0.057%

    No Known Activations