© 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. 89726
    Prev
    Next
    INDEX
    Explanations

    statements about official confirmations or announcements

    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
    azio
    -0.06
    ROL
    -0.06
    remen
    -0.06
    sf
    -0.06
    ÑĭÑĤ
    -0.06
     kla
    -0.06
    ova
    -0.06
    kt
    -0.06
     chance
    -0.06
    лÑĥÑĪ
    -0.06
    POSITIVE LOGITS
     bahwa
    0.09
     indeed
    0.09
     rằng
    0.08
    ibase
    0.07
     existence
    0.07
     Indeed
    0.07
    åŃĺåľ¨
    0.07
    abant
    0.07
    andel
    0.07
    receipt
    0.07
    Activations Density 0.007%

    No Known Activations