© 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. 103869
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "life."

    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
    itoris
    -0.07
    opot
    -0.07
    uales
    -0.07
    enet
    -0.07
    materials
    -0.06
    cosa
    -0.06
     ucwords
    -0.06
    Äįná
    -0.06
    assen
    -0.06
    nth
    -0.06
    POSITIVE LOGITS
    ØŃÙĩ
    0.07
    ="{!!
    0.06
     sensit
    0.06
    berger
    0.06
    boy
    0.06
     Antony
    0.06
    alam
    0.06
     Phen
    0.06
     gravy
    0.06
    aram
    0.06
    Activations Density 0.001%

    No Known Activations