© 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. 1343
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and hardware solutions

    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
    ertz
    -0.08
     Oc
    -0.07
    ibern
    -0.07
    267
    -0.07
    IPC
    -0.06
    ustos
    -0.06
    нин
    -0.06
    umas
    -0.06
     lúc
    -0.06
     cort
    -0.06
    POSITIVE LOGITS
     hardware
    0.12
    hardware
    0.10
     devices
    0.09
     Hardware
    0.07
     boards
    0.07
     device
    0.07
    devices
    0.07
     HARD
    0.06
    physical
    0.06
    czy
    0.06
    Activations Density 0.101%

    No Known Activations