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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 107263
    Prev
    Next
    INDEX
    Explanations

    references to elevators or lifts and their related actions

    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
    UNET
    -0.08
    анка
    -0.07
    aeda
    -0.07
    èĹ
    -0.07
    ofile
    -0.06
    istrate
    -0.06
    Ñĥже
    -0.06
    ãĥĬãĥ¼
    -0.06
    ož
    -0.06
    abus
    -0.06
    POSITIVE LOGITS
     Lobby
    0.07
     èIJ
    0.07
    adies
    0.07
     whisk
    0.06
     shaft
    0.06
    artment
    0.06
    lobby
    0.06
    ίÏĥ
    0.06
    indi
    0.06
     Tall
    0.06
    Activations Density 0.003%

    No Known Activations