© 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. 95942
    Prev
    Next
    INDEX
    Explanations

    terms related to competition and performance metrics

    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
     meis
    -0.07
     kvin
    -0.06
    .slim
    -0.06
    amar
    -0.06
    à¹ģà¸Ĺà¸Ļ
    -0.06
    berapa
    -0.06
    Untitled
    -0.06
    anken
    -0.06
    rada
    -0.06
    unks
    -0.05
    POSITIVE LOGITS
     advantage
    0.09
    ARGIN
    0.08
     superiority
    0.08
     Advantage
    0.07
    Difference
    0.07
    å·®
    0.07
    Mismatch
    0.07
     Ryder
    0.07
     advantages
    0.06
     Îļα
    0.06
    Activations Density 0.003%

    No Known Activations