© 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. 116367
    Prev
    Next
    INDEX
    Explanations

    phrases related to website usage and data privacy

    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
    ãĥ¼ãĤº
    -0.08
    berman
    -0.07
     spel
    -0.07
    aggio
    -0.07
    Ïģη
    -0.07
    .hm
    -0.07
    åı
    -0.06
    οÏħÏĤ
    -0.06
    ((&
    -0.06
    ãĤĤãģĨ
    -0.06
    POSITIVE LOGITS
    ritel
    0.07
    axe
    0.06
     handleMessage
    0.06
    GED
    0.06
    alim
    0.06
     recl
    0.06
    emma
    0.06
     mun
    0.06
     Reeves
    0.06
     Rowe
    0.06
    Activations Density 0.004%

    No Known Activations