© 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. 94023
    Prev
    Next
    INDEX
    Explanations

    phrases related to mathematical analysis or scientific research methodologies

    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
    uden
    -0.07
    ãĥ³ãĤ¸
    -0.06
    Ķ
    -0.06
    KeyListener
    -0.06
    atility
    -0.06
    rist
    -0.06
     peri
    -0.06
    uther
    -0.06
     пеÑĢ
    -0.06
    =<?=
    -0.06
    POSITIVE LOGITS
    ONGL
    0.08
     ninete
    0.07
    obox
    0.07
    ÙĨاÙħÙĩ
    0.06
     Abr
    0.06
     Katz
    0.06
     Fir
    0.06
    ì¦Ī
    0.06
    ime
    0.06
     Sé
    0.06
    Activations Density 0.039%

    No Known Activations