© 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. 108685
    Prev
    Next
    INDEX
    Explanations

    comparisons and questions regarding preferences or advantages

    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
    lle
    -0.07
    lg
    -0.07
    .scalablytyped
    -0.07
    okt
    -0.07
    âĢ«
    -0.06
    ãĤ¹ãĤ¿ãĥ¼
    -0.06
    CHO
    -0.06
    ought
    -0.06
     komb
    -0.06
    लब
    -0.06
    POSITIVE LOGITS
    :
    0.11
     either
    0.09
     EITHER
    0.08
    either
    0.08
    between
    0.07
    Either
    0.07
     Either
    0.07
    بÙĬÙĨ
    0.07
    whether
    0.07
    ():
    0.06
    Activations Density 0.013%

    No Known Activations