© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 93197
    Prev
    Next
    INDEX
    Explanations

    words related to locations and types of buildings

    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
     Beds
    -0.07
    rane
    -0.07
    Disposed
    -0.07
    uez
    -0.07
    rana
    -0.07
     beds
    -0.06
     benches
    -0.06
     bÃłn
    -0.06
     bench
    -0.06
    åŃĹ段
    -0.06
    POSITIVE LOGITS
     building
    0.10
     buildings
    0.10
    building
    0.08
     structure
    0.08
    structure
    0.08
     Building
    0.07
    ourcem
    0.07
     Buildings
    0.07
    Building
    0.07
     complexes
    0.07
    Activations Density 0.036%

    No Known Activations