© 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. 14417
    Prev
    Next
    INDEX
    Explanations

    concepts related to architecture and its societal implications

    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
     assort
    -0.07
     FY
    -0.07
    achuset
    -0.07
    eka
    -0.06
    /assets
    -0.06
     adult
    -0.06
    cus
    -0.06
    erton
    -0.06
    enic
    -0.06
    /setup
    -0.06
    POSITIVE LOGITS
     architects
    0.10
     architectural
    0.09
     architect
    0.09
     Architects
    0.09
     building
    0.09
     architecture
    0.09
     designers
    0.09
     Architecture
    0.09
    建çŃij
    0.08
    arch
    0.08
    Activations Density 0.026%

    No Known Activations