© 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. 18844
    Prev
    Next
    INDEX
    Explanations

    phrases related to the functioning and issues of mechanical parts or engines

    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
    ded
    -0.07
    зм
    -0.07
    reeze
    -0.07
    pac
    -0.07
    worker
    -0.07
    zimmer
    -0.06
    ipop
    -0.06
    út
    -0.06
    ãĥģãĥ£
    -0.06
    uled
    -0.06
    POSITIVE LOGITS
     starter
    0.08
     startup
    0.07
     startups
    0.07
     engine
    0.07
    anh
    0.07
    =start
    0.07
     rallies
    0.07
    starter
    0.07
     parking
    0.06
    -driving
    0.06
    Activations Density 0.028%

    No Known Activations