© 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. 18747
    Prev
    Next
    INDEX
    Explanations

    references to historical events and figures

    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
     Nack
    -0.08
    mins
    -0.08
    åĪļ
    -0.07
     minimum
    -0.06
    |min
    -0.06
     MIN
    -0.06
    ckt
    -0.06
    ritch
    -0.06
     Coff
    -0.06
     minced
    -0.06
    POSITIVE LOGITS
     Christianity
    0.07
     AD
    0.07
     decline
    0.07
     vitae
    0.06
     devast
    0.06
    .ai
    0.06
    LEEP
    0.06
     Dark
    0.06
     Islam
    0.06
     POD
    0.06
    Activations Density 0.026%

    No Known Activations