© 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. 6016
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to networking and server configuration

    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
    .Invariant
    -0.08
    zman
    -0.07
     èį
    -0.07
    à¸Ķย
    -0.07
    ledik
    -0.07
    ritch
    -0.06
    æ£ļ
    -0.06
    .PLL
    -0.06
     Heck
    -0.06
    ieder
    -0.06
    POSITIVE LOGITS
     port
    0.08
     host
    0.08
     address
    0.08
     Nat
    0.07
    ip
    0.07
    192
    0.07
     IP
    0.07
     "::
    0.07
     '::
    0.07
    quina
    0.07
    Activations Density 0.148%

    No Known Activations