© 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. 80882
    Prev
    Next
    INDEX
    Explanations

    concepts related to effective communication and information dissemination

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    Advertisement
    -0.06
    ooter
    -0.06
    <=(
    -0.06
     clim
    -0.06
     advert
    -0.06
    /pi
    -0.06
     tac
    -0.06
     ки
    -0.05
     rip
    -0.05
    eway
    -0.05
    POSITIVE LOGITS
     communication
    0.09
     communications
    0.09
    Communic
    0.07
    Affected
    0.07
    .SetParent
    0.07
    communication
    0.07
     Communication
    0.07
     communicator
    0.07
     information
    0.07
     comunic
    0.07
    Activations Density 0.002%

    No Known Activations