© 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. 104055
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant figures or statistics

    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
    igu
    -0.07
    ãĥ³ãĥĦ
    -0.07
    lessness
    -0.06
     importantly
    -0.06
     Z
    -0.06
    æ°ĹãģĮ
    -0.06
    klass
    -0.06
     N
    -0.06
     than
    -0.05
    .gov
    -0.05
    POSITIVE LOGITS
    oppins
    0.08
    ivial
    0.07
    OnChange
    0.07
    olan
    0.07
    ftime
    0.07
    LOAT
    0.07
    QRST
    0.07
    olare
    0.07
    /cgi
    0.07
    .getElementsByName
    0.07
    Activations Density 0.023%

    No Known Activations