© 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. 42784
    Prev
    Next
    INDEX
    Explanations

    occurrences of script tags in a web document

    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
    edo
    -0.07
    дÑĢеÑģ
    -0.06
    Äįi
    -0.06
    671
    -0.06
    anda
    -0.06
     Lamp
    -0.06
     GenerationType
    -0.06
    eing
    -0.06
    ":[{↵
    -0.06
    боÑĤ
    -0.06
    POSITIVE LOGITS
     ../
    0.06
     Tib
    0.06
     src
    0.06
     Howell
    0.06
    achu
    0.05
     fart
    0.05
    _dirty
    0.05
    adors
    0.05
    64
    0.05
    IBUT
    0.05
    Activations Density 0.004%

    No Known Activations