© 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. 42528
    Prev
    Next
    INDEX
    Explanations

    culinary descriptions and activities related to food preparation

    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
    ãĤ¦ãĤ©
    -0.07
    Ñĭл
    -0.07
    -Mart
    -0.07
    гл
    -0.06
    ä¸Ŀ
    -0.06
    .rl
    -0.06
    ocom
    -0.06
    ''''
    -0.06
    dle
    -0.06
    isle
    -0.06
    POSITIVE LOGITS
     Mich
    0.07
     mich
    0.07
     instagram
    0.06
     gast
    0.06
     za
    0.06
     Counter
    0.06
    _sa
    0.06
    ansson
    0.06
    onn
    0.06
    /rest
    0.06
    Activations Density 0.337%

    No Known Activations