© 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. 9-LLAMASCOPE-RES-131K
    11. 94316
    Prev
    Next
    INDEX
    Explanations

    references to infrastructure and transportation networks

    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
    ronics
    -0.05
     auth
    -0.05
    lug
    -0.05
    åĪļæīį
    -0.05
    ailing
    -0.05
     Tos
    -0.05
     extends
    -0.05
    cha
    -0.05
    eyer
    -0.05
     Tall
    -0.05
    POSITIVE LOGITS
    ién
    0.09
    бÑĥÑĤ
    0.08
    unken
    0.08
    icone
    0.08
    Indented
    0.07
    logan
    0.07
    /interface
    0.07
     tarif
    0.07
     Kund
    0.07
    tar
    0.07
    Activations Density 0.015%

    No Known Activations