© 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. 73101
    Prev
    Next
    INDEX
    Explanations

    terms related to public transportation systems, specifically subways and metros

    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
    udes
    -0.07
    UNET
    -0.07
    xec
    -0.07
    eral
    -0.06
    ped
    -0.06
    edy
    -0.06
    okit
    -0.06
    fox
    -0.06
    ful
    -0.06
     helicopt
    -0.06
    POSITIVE LOGITS
    /bus
    0.09
    /train
    0.08
    izzo
    0.08
    ogie
    0.07
    /logger
    0.07
    SCO
    0.07
    สาย
    0.07
     اÙĦÙĪÙĦ
    0.07
    iasi
    0.07
    logan
    0.07
    Activations Density 0.012%

    No Known Activations