© 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. 116575
    Prev
    Next
    INDEX
    Explanations

    key moments of decision-making or pivotal events in a narrative

    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
    oga
    -0.08
    inyin
    -0.07
    unn
    -0.07
     Ø¢Ùħ
    -0.06
    ÑĮÑİ
    -0.06
    edback
    -0.06
    angel
    -0.06
    ">ÃĹ</
    -0.06
    ogle
    -0.06
     Infer
    -0.06
    POSITIVE LOGITS
     magic
    0.07
     MAGIC
    0.07
     Magic
    0.06
    akens
    0.06
    blas
    0.06
     accident
    0.06
    663
    0.06
    avery
    0.06
    æĥł
    0.06
    agic
    0.06
    Activations Density 0.018%

    No Known Activations