© 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. 9-LLAMASCOPE-RES-131K
    11. 93953
    Prev
    Next
    INDEX
    Explanations

    terms related to food, cooking, and email delivery processes

    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
    duino
    -0.06
    uchar
    -0.06
    mi
    -0.06
    SED
    -0.06
    utan
    -0.06
     wr
    -0.05
    Ìģ
    -0.05
    #:
    -0.05
    opa
    -0.05
    aged
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.09
    âĹİ
    0.08
    .LookAndFeel
    0.07
    ÛĮزÛĮ
    0.07
    .isDefined
    0.07
    647
    0.06
    ieten
    0.06
    izia
    0.06
    ãĤ¾
    0.06
    léd
    0.06
    Activations Density 0.002%

    No Known Activations