© 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. 14209
    Prev
    Next
    INDEX
    Explanations

    references to teenage girls and their associated fan culture

    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
     Záp
    -0.07
    reeze
    -0.06
    amd
    -0.06
    á»IJ
    -0.06
    OG
    -0.06
    jours
    -0.06
    meli
    -0.06
    landers
    -0.06
    .rdf
    -0.06
    nty
    -0.06
    POSITIVE LOGITS
     audiences
    0.08
     readers
    0.07
     reader
    0.07
    reader
    0.07
     audience
    0.07
     viewers
    0.07
     оÑĤв
    0.06
     viewer
    0.06
    票
    0.06
     éĿĴ
    0.06
    Activations Density 0.044%

    No Known Activations