© 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. 91611
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pop" and its variations

    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
    umin
    -0.07
    éĢĶ
    -0.07
    æij
    -0.06
    溪
    -0.06
    anter
    -0.06
    (always
    -0.06
    von
    -0.06
     McCartney
    -0.06
    atform
    -0.06
    /operator
    -0.06
    POSITIVE LOGITS
     popping
    0.07
    .Popup
    0.07
    PING
    0.07
     popped
    0.06
    ularity
    0.06
    cock
    0.06
     Pop
    0.06
    Pop
    0.06
    ánu
    0.06
    /pop
    0.06
    Activations Density 0.006%

    No Known Activations