© 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. 89807
    Prev
    Next
    INDEX
    Explanations

    phrases related to age restrictions and supervision requirements for website use

    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
     ÑĥлÑĭ
    -0.07
    izia
    -0.07
    640
    -0.06
    ĴĮ
    -0.06
    Å¡lo
    -0.06
    .RemoveAll
    -0.06
     voluntary
    -0.06
    fee
    -0.06
    620
    -0.06
     Ing
    -0.06
    POSITIVE LOGITS
    urm
    0.07
    aign
    0.07
    aload
    0.07
     supervised
    0.06
    ihar
    0.06
    inos
    0.06
    ervised
    0.06
     parental
    0.06
    ATURE
    0.06
    hai
    0.06
    Activations Density 0.003%

    No Known Activations