© 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. 80840
    Prev
    Next
    INDEX
    Explanations

    references to the Boeing company and its aircraft

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ially
    -0.08
    enance
    -0.07
    elib
    -0.07
    Enums
    -0.07
    ово
    -0.07
    anter
    -0.07
    akit
    -0.06
    åŁŁ
    -0.06
    xing
    -0.06
    ãĥªãĥ¼ãĤº
    -0.06
    POSITIVE LOGITS
     rar
    0.07
    162
    0.07
    anical
    0.06
    ĺ
    0.06
    izia
    0.06
    emia
    0.06
    arde
    0.06
     saddle
    0.06
    -formed
    0.06
    alty
    0.06
    Activations Density 0.012%

    No Known Activations